diff --git a/chat_template.jinja b/chat_template.jinja index 6db75032daf1858ac11ee2fa8eb1cec31751ac13..93022eb9ceec98f50e7a510841850f7f2e952d9d 100644 --- a/chat_template.jinja +++ b/chat_template.jinja @@ -8,7 +8,7 @@ {%- set think_begin_token = '' -%} {%- set think_end_token = '' -%} {%- set image_token = ']<]image[>[' -%} -{%- set frame_token = ']<]frame[>[' -%} +{%- set video_token = ']<]video[>[' -%} {#- Thinking mode: "enabled" / "disabled" / "adaptive" / not defined -#} {#- Recursive XML renderer for tool_call arguments ======================== -#} {#- None values are intentionally skipped in mapping iteration so that @@ -49,8 +49,8 @@ {{- item.text }} {%- elif item is mapping and item.type == 'image' -%} {{- image_token }} - {%- elif item is mapping and item.type == 'frame' -%} - {{- frame_token}} + {%- elif item is mapping and item.type == 'video' -%} + {{- video_token}} {%- elif item is string -%} {{- item }} {%- endif -%} @@ -212,8 +212,8 @@ {%- for tr in message.content -%} {%- if tr is mapping and tr.type is defined and tr.type == 'image' -%} {{- image_token }} - {%- elif tr is mapping and tr.type is defined and tr.type == 'frame' -%} - {{- frame_token }} + {%- elif tr is mapping and tr.type is defined and tr.type == 'video' -%} + {{- video_token }} {%- else -%} {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }} {%- endif -%} diff --git a/config.json b/config.json index cb650f789932f183b8e53034ee877903a7ce647e..545e60d488458cf2b9f5d62a8e2658d51dc268bc 100644 --- a/config.json +++ b/config.json @@ -325,177 +325,72 @@ }, "exclude": [ "language_model.lm_head", + "language_model.model.layers.0.mlp.down_proj", + "language_model.model.layers.0.mlp.gate_proj", + "language_model.model.layers.0.mlp.up_proj", + "language_model.model.layers.1.mlp.down_proj", + "language_model.model.layers.1.mlp.gate_proj", + "language_model.model.layers.1.mlp.up_proj", "language_model.model.layers.10.block_sparse_moe.gate", - "language_model.model.layers.10.self_attn.index_k_proj", - "language_model.model.layers.10.self_attn.index_q_proj", "language_model.model.layers.11.block_sparse_moe.gate", - "language_model.model.layers.11.self_attn.index_k_proj", - "language_model.model.layers.11.self_attn.index_q_proj", "language_model.model.layers.12.block_sparse_moe.gate", - "language_model.model.layers.12.self_attn.index_k_proj", - "language_model.model.layers.12.self_attn.index_q_proj", "language_model.model.layers.13.block_sparse_moe.gate", - "language_model.model.layers.13.self_attn.index_k_proj", - "language_model.model.layers.13.self_attn.index_q_proj", "language_model.model.layers.14.block_sparse_moe.gate", - "language_model.model.layers.14.self_attn.index_k_proj", - "language_model.model.layers.14.self_attn.index_q_proj", "language_model.model.layers.15.block_sparse_moe.gate", - "language_model.model.layers.15.self_attn.index_k_proj", - "language_model.model.layers.15.self_attn.index_q_proj", "language_model.model.layers.16.block_sparse_moe.gate", - "language_model.model.layers.16.self_attn.index_k_proj", - "language_model.model.layers.16.self_attn.index_q_proj", "language_model.model.layers.17.block_sparse_moe.gate", - "language_model.model.layers.17.self_attn.index_k_proj", - "language_model.model.layers.17.self_attn.index_q_proj", "language_model.model.layers.18.block_sparse_moe.gate", - "language_model.model.layers.18.self_attn.index_k_proj", - "language_model.model.layers.18.self_attn.index_q_proj", "language_model.model.layers.19.block_sparse_moe.gate", - "language_model.model.layers.19.self_attn.index_k_proj", - "language_model.model.layers.19.self_attn.index_q_proj", + "language_model.model.layers.2.mlp.down_proj", + "language_model.model.layers.2.mlp.gate_proj", + "language_model.model.layers.2.mlp.up_proj", "language_model.model.layers.20.block_sparse_moe.gate", - "language_model.model.layers.20.self_attn.index_k_proj", - "language_model.model.layers.20.self_attn.index_q_proj", "language_model.model.layers.21.block_sparse_moe.gate", - "language_model.model.layers.21.self_attn.index_k_proj", - "language_model.model.layers.21.self_attn.index_q_proj", "language_model.model.layers.22.block_sparse_moe.gate", - "language_model.model.layers.22.self_attn.index_k_proj", - "language_model.model.layers.22.self_attn.index_q_proj", "language_model.model.layers.23.block_sparse_moe.gate", - "language_model.model.layers.23.self_attn.index_k_proj", - "language_model.model.layers.23.self_attn.index_q_proj", "language_model.model.layers.24.block_sparse_moe.gate", - "language_model.model.layers.24.self_attn.index_k_proj", - "language_model.model.layers.24.self_attn.index_q_proj", "language_model.model.layers.25.block_sparse_moe.gate", - "language_model.model.layers.25.self_attn.index_k_proj", - "language_model.model.layers.25.self_attn.index_q_proj", "language_model.model.layers.26.block_sparse_moe.gate", - "language_model.model.layers.26.self_attn.index_k_proj", - "language_model.model.layers.26.self_attn.index_q_proj", "language_model.model.layers.27.block_sparse_moe.gate", - "language_model.model.layers.27.self_attn.index_k_proj", - "language_model.model.layers.27.self_attn.index_q_proj", "language_model.model.layers.28.block_sparse_moe.gate", - "language_model.model.layers.28.self_attn.index_k_proj", - "language_model.model.layers.28.self_attn.index_q_proj", "language_model.model.layers.29.block_sparse_moe.gate", - "language_model.model.layers.29.self_attn.index_k_proj", - "language_model.model.layers.29.self_attn.index_q_proj", "language_model.model.layers.3.block_sparse_moe.gate", - "language_model.model.layers.3.self_attn.index_k_proj", - "language_model.model.layers.3.self_attn.index_q_proj", "language_model.model.layers.30.block_sparse_moe.gate", - "language_model.model.layers.30.self_attn.index_k_proj", - "language_model.model.layers.30.self_attn.index_q_proj", "language_model.model.layers.31.block_sparse_moe.gate", - "language_model.model.layers.31.self_attn.index_k_proj", - "language_model.model.layers.31.self_attn.index_q_proj", "language_model.model.layers.32.block_sparse_moe.gate", - "language_model.model.layers.32.self_attn.index_k_proj", - "language_model.model.layers.32.self_attn.index_q_proj", "language_model.model.layers.33.block_sparse_moe.gate", - "language_model.model.layers.33.self_attn.index_k_proj", - "language_model.model.layers.33.self_attn.index_q_proj", "language_model.model.layers.34.block_sparse_moe.gate", - "language_model.model.layers.34.self_attn.index_k_proj", - "language_model.model.layers.34.self_attn.index_q_proj", "language_model.model.layers.35.block_sparse_moe.gate", - "language_model.model.layers.35.self_attn.index_k_proj", - "language_model.model.layers.35.self_attn.index_q_proj", "language_model.model.layers.36.block_sparse_moe.gate", - "language_model.model.layers.36.self_attn.index_k_proj", - "language_model.model.layers.36.self_attn.index_q_proj", "language_model.model.layers.37.block_sparse_moe.gate", - "language_model.model.layers.37.self_attn.index_k_proj", - "language_model.model.layers.37.self_attn.index_q_proj", "language_model.model.layers.38.block_sparse_moe.gate", - "language_model.model.layers.38.self_attn.index_k_proj", - "language_model.model.layers.38.self_attn.index_q_proj", "language_model.model.layers.39.block_sparse_moe.gate", - "language_model.model.layers.39.self_attn.index_k_proj", - "language_model.model.layers.39.self_attn.index_q_proj", "language_model.model.layers.4.block_sparse_moe.gate", - "language_model.model.layers.4.self_attn.index_k_proj", - "language_model.model.layers.4.self_attn.index_q_proj", "language_model.model.layers.40.block_sparse_moe.gate", - "language_model.model.layers.40.self_attn.index_k_proj", - "language_model.model.layers.40.self_attn.index_q_proj", "language_model.model.layers.41.block_sparse_moe.gate", - "language_model.model.layers.41.self_attn.index_k_proj", - "language_model.model.layers.41.self_attn.index_q_proj", "language_model.model.layers.42.block_sparse_moe.gate", - "language_model.model.layers.42.self_attn.index_k_proj", - "language_model.model.layers.42.self_attn.index_q_proj", "language_model.model.layers.43.block_sparse_moe.gate", - "language_model.model.layers.43.self_attn.index_k_proj", - "language_model.model.layers.43.self_attn.index_q_proj", "language_model.model.layers.44.block_sparse_moe.gate", - "language_model.model.layers.44.self_attn.index_k_proj", - "language_model.model.layers.44.self_attn.index_q_proj", "language_model.model.layers.45.block_sparse_moe.gate", - "language_model.model.layers.45.self_attn.index_k_proj", - "language_model.model.layers.45.self_attn.index_q_proj", "language_model.model.layers.46.block_sparse_moe.gate", - "language_model.model.layers.46.self_attn.index_k_proj", - "language_model.model.layers.46.self_attn.index_q_proj", "language_model.model.layers.47.block_sparse_moe.gate", - "language_model.model.layers.47.self_attn.index_k_proj", - "language_model.model.layers.47.self_attn.index_q_proj", "language_model.model.layers.48.block_sparse_moe.gate", - "language_model.model.layers.48.self_attn.index_k_proj", - "language_model.model.layers.48.self_attn.index_q_proj", "language_model.model.layers.49.block_sparse_moe.gate", - "language_model.model.layers.49.self_attn.index_k_proj", - "language_model.model.layers.49.self_attn.index_q_proj", "language_model.model.layers.5.block_sparse_moe.gate", - "language_model.model.layers.5.self_attn.index_k_proj", - "language_model.model.layers.5.self_attn.index_q_proj", "language_model.model.layers.50.block_sparse_moe.gate", - "language_model.model.layers.50.self_attn.index_k_proj", - "language_model.model.layers.50.self_attn.index_q_proj", "language_model.model.layers.51.block_sparse_moe.gate", - "language_model.model.layers.51.self_attn.index_k_proj", - "language_model.model.layers.51.self_attn.index_q_proj", "language_model.model.layers.52.block_sparse_moe.gate", - "language_model.model.layers.52.self_attn.index_k_proj", - "language_model.model.layers.52.self_attn.index_q_proj", "language_model.model.layers.53.block_sparse_moe.gate", - "language_model.model.layers.53.self_attn.index_k_proj", - "language_model.model.layers.53.self_attn.index_q_proj", "language_model.model.layers.54.block_sparse_moe.gate", - "language_model.model.layers.54.self_attn.index_k_proj", - "language_model.model.layers.54.self_attn.index_q_proj", "language_model.model.layers.55.block_sparse_moe.gate", - "language_model.model.layers.55.self_attn.index_k_proj", - "language_model.model.layers.55.self_attn.index_q_proj", "language_model.model.layers.56.block_sparse_moe.gate", - "language_model.model.layers.56.self_attn.index_k_proj", - "language_model.model.layers.56.self_attn.index_q_proj", "language_model.model.layers.57.block_sparse_moe.gate", - "language_model.model.layers.57.self_attn.index_k_proj", - "language_model.model.layers.57.self_attn.index_q_proj", "language_model.model.layers.58.block_sparse_moe.gate", - "language_model.model.layers.58.self_attn.index_k_proj", - "language_model.model.layers.58.self_attn.index_q_proj", "language_model.model.layers.59.block_sparse_moe.gate", - "language_model.model.layers.59.self_attn.index_k_proj", - "language_model.model.layers.59.self_attn.index_q_proj", "language_model.model.layers.6.block_sparse_moe.gate", - "language_model.model.layers.6.self_attn.index_k_proj", - "language_model.model.layers.6.self_attn.index_q_proj", "language_model.model.layers.7.block_sparse_moe.gate", - "language_model.model.layers.7.self_attn.index_k_proj", - "language_model.model.layers.7.self_attn.index_q_proj", "language_model.model.layers.8.block_sparse_moe.gate", - "language_model.model.layers.8.self_attn.index_k_proj", - "language_model.model.layers.8.self_attn.index_q_proj", "language_model.model.layers.9.block_sparse_moe.gate", - "language_model.model.layers.9.self_attn.index_k_proj", - "language_model.model.layers.9.self_attn.index_q_proj", "multi_modal_projector.linear_1", "multi_modal_projector.linear_2", "patch_merge_mlp.linear_1", @@ -807,7 +702,7 @@ "kv_cache_quant_config": {}, "kv_cache_post_rope": false, "quant_mode": "eager_mode", - "version": "0.12+unknown", + "version": "0.12+5684ef6391b", "export": { "kv_cache_group": [], "min_kv_scale": 0.0, diff --git a/figures/benchmark.jpeg b/figures/benchmark.jpeg new file mode 100644 index 0000000000000000000000000000000000000000..5bc1bdd97b088885678861765fa6b3fa6cd7c55c --- /dev/null +++ b/figures/benchmark.jpeg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4bc02e54f508f540e71a9286905477c780934bb79c0b17cd5892b6338313e57 +size 4417149 diff --git a/figures/efficiency_gqa_vs_msa.png b/figures/efficiency_gqa_vs_msa.png new file mode 100644 index 0000000000000000000000000000000000000000..cf0c76a949f52bfb48a3332760933a213edc224c Binary files /dev/null and b/figures/efficiency_gqa_vs_msa.png differ diff --git a/figures/logo.svg b/figures/logo.svg new file mode 100644 index 0000000000000000000000000000000000000000..972b41cdb04e1ab4c2b94fa0c35df0c80a5151a2 --- /dev/null +++ b/figures/logo.svg @@ -0,0 +1,16 @@ + + + + + + + + + + + + + + + + diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..54806f9d4ea503f2d1afa468de37764acbbaa97d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "bos_token_id": 200019, + "do_sample": true, + "eos_token_id": 200020, + "temperature": 1.0, + "top_p": 0.95, + "transformers_version": "4.46.1" +} \ No newline at end of file diff --git a/model-00001-of-00059.safetensors b/model-00001-of-00059.safetensors index 9f28a7c49038f59b8e36e158c510ddd313aa670b..6b69b4deef1df30059b8b7e35fed77d00118a4a3 100644 --- a/model-00001-of-00059.safetensors +++ b/model-00001-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f28f4bdafbc249115cfea07ca43af23949684bbd525dfa0b2f53b0a3a318d652 -size 5144153184 +oid sha256:cbfdba9b4241f6455037ab50c79cc7937e4fffc762dbf4911f9bad5ce70e37c8 +size 5476813528 diff --git a/model-00002-of-00059.safetensors b/model-00002-of-00059.safetensors index 4b293fb3136bd00697170d68a20c742d95c88a07..09747adae14426f01725163e49a2eb4b22a038b5 100644 --- a/model-00002-of-00059.safetensors +++ b/model-00002-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fe056fb6c9b3920d83f48fd71452a9dc299a38664bfd018e758dcac0a56224b8 -size 3001670712 +oid sha256:a0f2c893ae5430467b1b7a369e71e2e9e69b0bd996d00b0643ff99dbb7a69aec +size 3666991696 diff --git a/model-00003-of-00059.safetensors b/model-00003-of-00059.safetensors index 6d7af56e240b175f4b439bbee10da21c23dbe878..61a17510a03e9b90f9ff0f5482c87a06382e9910 100644 --- a/model-00003-of-00059.safetensors +++ b/model-00003-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cbb03f24f09dbf41c718c906a17db276424de86ecfa5feb6809975ce73672955 -size 4329521504 +oid sha256:ea1684d2e3ca216023e655563f1dea069d950ffd1317261fe649840695612e65 +size 4325592160 diff --git a/model-00004-of-00059.safetensors b/model-00004-of-00059.safetensors index 690f5e18cf248d6f219102618b46d89b40e3e145..b7ef46f95d62d1b229ba1ceb28b27535f7c6498d 100644 --- a/model-00004-of-00059.safetensors +++ b/model-00004-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e6a3e5e7a5d3340a331d5824636bb7011e51b2046ac7dec49ba834101c064862 -size 4329521496 +oid sha256:5e2c6f38479783138b0753d30bf876e16f57f7d579553ec491680b971a06d182 +size 4325592152 diff --git a/model-00005-of-00059.safetensors b/model-00005-of-00059.safetensors index c5e2a759d890b3aa5c51e19b919df23d57379e06..e538c1266215f99ba265b7ecdbae6dbfd15fd790 100644 --- a/model-00005-of-00059.safetensors +++ b/model-00005-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8e8530b46a242f1e12548c9012b4439ba263ea42f288587805c61e0faa232cbb -size 4329521496 +oid sha256:66b0f2487146b6cbfd0e770f0ca0230f76e63f22b1018f4793039a7749dc9d42 +size 4325592152 diff --git a/model-00006-of-00059.safetensors b/model-00006-of-00059.safetensors index b580faf359ac881fc64ab5e7045b6eafb5252ed2..424014aa1ccdb2cfe534de736a171c8949d32c57 100644 --- a/model-00006-of-00059.safetensors +++ b/model-00006-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e790cc709b7cff2e5e94e1404c2f7e4f2ed6c80b0749b8f6bbc768f8b734d7b5 -size 4329521496 +oid sha256:25a67e5f4d06c60afdabc9c390093b9005fd186e79050a6e88c2f289e2e77b09 +size 4325592152 diff --git a/model-00007-of-00059.safetensors b/model-00007-of-00059.safetensors index 9bd6750afcb1eba7eb9735e3bf3daad833834826..5337e3f38750514ef818725940033825f8ec7ee0 100644 --- a/model-00007-of-00059.safetensors +++ b/model-00007-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:43acfe521267deb94a7fe34108196a6d53702ed69e42c60dceee5e46a2305b9d -size 4329521496 +oid sha256:ff993fdd56ece5a1dd7ccf4707ae9b52fe9b60533c99a8c6d7d9337899b66160 +size 4325592152 diff --git a/model-00008-of-00059.safetensors b/model-00008-of-00059.safetensors index 0479bfb198b26823ce591f30a16832d86b1b7012..1a516597ff8bdb008d7a311110d4c9c810fbf2e5 100644 --- a/model-00008-of-00059.safetensors +++ b/model-00008-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:96b37fb353e67fe8852353f55f7858c863c72b18405c55012c65e27a1faad1cc -size 4329521496 +oid sha256:f33415b2afa537e835cedd5844970773ddbdca5ce3c4fbdfabf152be40eb7a51 +size 4325592152 diff --git a/model-00009-of-00059.safetensors b/model-00009-of-00059.safetensors index 70dc6b3825448bc861f241582c6406094aeff7d2..04ada700d8f5a159cbd845f1e11df285066928de 100644 --- a/model-00009-of-00059.safetensors +++ b/model-00009-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c8187d221d773de1bb041b3749fa2fa07f634a5eee2d3459da750954bca5ee9a -size 4329521496 +oid sha256:eb18683fc6361dc6a41ebea1888d21529d3f8d8d9d1562f59fdef94077549adc +size 4325592152 diff --git a/model-00010-of-00059.safetensors b/model-00010-of-00059.safetensors index aec9de1008090cee80ca5b5a0d93e1f78f773c03..8309335bf9878c8f9306c5eeccb1bf8e5edc4573 100644 --- a/model-00010-of-00059.safetensors +++ b/model-00010-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8310cbcbc61bddc064e47492b38f00d51ca53c20e99a2154e04bc57d61ba9740 -size 4329522296 +oid sha256:474004dbd736515d2ed03b81225eba4b80e262180777f3b61a4623233ac8172f +size 4325592952 diff --git a/model-00011-of-00059.safetensors b/model-00011-of-00059.safetensors index 1201741059ecee0546d0d25fc56f6fb6795a19cc..bbe6c6e3ca4a8d7fd1690cea7015eb19c23b711c 100644 --- a/model-00011-of-00059.safetensors +++ b/model-00011-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:50a24414872b2386b72d733bcdf82fb7b28226d80ee925711c6b690197b51324 -size 4329522296 +oid sha256:fcd3419bfb98b43fae13be9ac43117adfaa2776237ef94f34be55c05220ce270 +size 4325592952 diff --git a/model-00012-of-00059.safetensors b/model-00012-of-00059.safetensors index 0b8b2711a8746ae0160e62b74bd36dcac310ed53..4b7deca1c0cfc12965a57095c3da5f87e675a430 100644 --- a/model-00012-of-00059.safetensors +++ b/model-00012-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3c26e3c9385167112cb2b8e9a00024625e6d6991cf2c2324db75c8a3645a988d -size 4329522296 +oid sha256:e01e8085ce34f787c1db8e15036b3eab2395be9ba043b9f06d9508cf66203716 +size 4325592952 diff --git a/model-00013-of-00059.safetensors b/model-00013-of-00059.safetensors index 7ddc2650d3ac8ebea260fa79307fe6049b83e259..ae99c1b7752d18eca4f04bcffbc3ce5e273c4b33 100644 --- a/model-00013-of-00059.safetensors +++ b/model-00013-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e329a90cf42b210b805049933c88045155af63858de4663e999ccfd30e6d5918 -size 4329522296 +oid sha256:ac6bef8d73f9621545210c3dfb7942227d0138d71486636864b530ee302d7f87 +size 4325592952 diff --git a/model-00014-of-00059.safetensors b/model-00014-of-00059.safetensors index 07a1407b55db7ac49bdbae5851e31b2e6e155041..a7772153536a496fe016670bde69e00b7d597c33 100644 --- a/model-00014-of-00059.safetensors +++ b/model-00014-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fa8b2b41c5dd3485d8aa187ed92e113b01e3bad5fb4059a5d36b90407ec5f947 -size 4329522296 +oid sha256:c4651bcde0da735519a824afb3b08145a73fa094c80510715121669953c777e1 +size 4325592952 diff --git a/model-00015-of-00059.safetensors b/model-00015-of-00059.safetensors index d2334fae7cd025048c6d5ccf2ce78f610e436237..ef3158bb320c09257147b9662b8a166aefe9074f 100644 --- a/model-00015-of-00059.safetensors +++ b/model-00015-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a8877593ba6e3087d8f008f3ecccf2b6268f0263ede5f8a56d84f4fac28dadce -size 4329522296 +oid sha256:986d278785f7cdaac8fb6e01fb4569f01429ce4d6355ede542d433e9308c9127 +size 4325592952 diff --git a/model-00016-of-00059.safetensors b/model-00016-of-00059.safetensors index 2d27c243be496b9ea5f83ac974fd18840271ee7d..6bb79254a2c6a11d4aceeb7bf8468fb68f8feed3 100644 --- a/model-00016-of-00059.safetensors +++ b/model-00016-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:576b5d5b3e3142de03bb295b5a51dccf5b16fb23bc1f9967039df039d346a3a6 -size 4329522296 +oid sha256:2046ebd3c5e78411e940c8dc2d7ca770120def6b35c430e41b1117f89d7166d5 +size 4325592952 diff --git a/model-00017-of-00059.safetensors b/model-00017-of-00059.safetensors index 970266262820cc7b578fe58004669873231b6359..892b9efec343c19b3e587e1931f5072c7b18b50d 100644 --- a/model-00017-of-00059.safetensors +++ b/model-00017-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:63a9edc7a10bea4bb133bde02b625954f8d7d0a002b3125f90928a12163f1158 -size 4329522296 +oid sha256:2dfbaa5685f4da3e04f348232b9fa02d8c57875e984d2b0101fae3103b53bf9d +size 4325592952 diff --git a/model-00018-of-00059.safetensors b/model-00018-of-00059.safetensors index 9c1dfdd0fe976cbac4abd0b02d0e245e6b716d7f..28a109d9097f45a1704ca73e4d315c0b5665d784 100644 --- a/model-00018-of-00059.safetensors +++ b/model-00018-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:df1b3b9bb35207109812e11f592b6f02ed737e10c1a8788fbe2cf7181fe4a14c -size 4329522296 +oid sha256:20dab737f65564f5d874d144ae9509c14e85649e8a40281ebb734b0d01c10bd2 +size 4325592952 diff --git a/model-00019-of-00059.safetensors b/model-00019-of-00059.safetensors index 50fef709c3500e1b84e7183fc5f1fcba680a9425..350f055e215a6821cd8c46cfb45f0c36f7e55679 100644 --- a/model-00019-of-00059.safetensors +++ b/model-00019-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:afe73087dcdf656d29c538c24b9b6411682c4d3f127b2eb48662b7c2b724705c -size 4329522296 +oid sha256:6b6d4f78e097843243ddde5564a5528dbe288a5219a8f4e2f1f2a205eee06c67 +size 4325592952 diff --git a/model-00020-of-00059.safetensors b/model-00020-of-00059.safetensors index 10c853b5a653a190ba2b2155646aac914fbe0a3c..bcd87fc13511d73fa735eb7299211b04749c5023 100644 --- a/model-00020-of-00059.safetensors +++ b/model-00020-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4772f3454013b665d1864926c5b1837c098d93f538bcde8194738f38247b4797 -size 4329522296 +oid sha256:c8b2d0241d627fe373a0d5faadf2d94ce7dd83cefb9983715082588ae81475f3 +size 4325592952 diff --git a/model-00021-of-00059.safetensors b/model-00021-of-00059.safetensors index dab54aa9b18b38ecb12eed258796c437241a70d0..88f3070b3e1be087752861148b2e3e6a50ff11ef 100644 --- a/model-00021-of-00059.safetensors +++ b/model-00021-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5698abf857083a932820e21ada2f6112eba48beb59371e7979392704b30d18a1 -size 4329522296 +oid sha256:a09a7d9b0d377014af4ca32674e826d4516e88063f7d438ca45b3bf5500ddf52 +size 4325592952 diff --git a/model-00022-of-00059.safetensors b/model-00022-of-00059.safetensors index 9f268d4de2e2d0e854ee0ce1dde3f2328cb122a3..3780cfeb91bdbf094b9e7c30f0ebce966c690b52 100644 --- a/model-00022-of-00059.safetensors +++ b/model-00022-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d44e9d08cc9636b0f174d8ee68aef71238f1631ec362d102416f3620e3edac87 -size 4329522296 +oid sha256:75be1f95230f254577723ddb692238d363f8be720569168b4ec9c13a9816baed +size 4325592952 diff --git a/model-00023-of-00059.safetensors b/model-00023-of-00059.safetensors index 1d3d7e3114515df40ea991792ecb7114ce22ec0f..bed13a2412fda689af81db5934b891de7d62b0bf 100644 --- a/model-00023-of-00059.safetensors +++ b/model-00023-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:590a212ca2fe70e4ed120d7ce4a4b84cf90694c97acbc8a08d22beee8eb647f2 -size 4329522296 +oid sha256:cf68eef99b975f550fa872c3b50b364b88269b489dcdf9b4280c8d3667fd4343 +size 4325592952 diff --git a/model-00024-of-00059.safetensors b/model-00024-of-00059.safetensors index b5ba822f10c11b18fdf29707e42fd00ca6f2831f..dfdf2539012e3ed76724a616b375168424425e85 100644 --- a/model-00024-of-00059.safetensors +++ b/model-00024-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7c9287f2c1a1a3f0fa79ffe060461b19cf895a327ef4b7e78fe3f54f6668b336 -size 4329522296 +oid sha256:b10e28ce8bab36f2852604a01b871f8a38d2f0401632ada99557f31248e3ee66 +size 4325592952 diff --git a/model-00025-of-00059.safetensors b/model-00025-of-00059.safetensors index 7f68dfa2c60fb04563421718b9db6dfe58b63087..098c8ae300f48bba93ec7f9c55987df3016cf6e0 100644 --- a/model-00025-of-00059.safetensors +++ b/model-00025-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d8775309024fa917e70a7638b2b5dfff525496e4b9c8636ebc5d1011d91a374e -size 1451684976 +oid sha256:7459a9bf592c2b294ed3f21fe43f9f31ea5d2bc68417e6989389f467b4d0e373 +size 1447755632 diff --git a/model-00026-of-00059.safetensors b/model-00026-of-00059.safetensors index a8047144da861b20be7f9ec7416c2c7d81dccd25..76860cc41f7be76c01e42b7d8d77cc7dacbb8260 100644 --- a/model-00026-of-00059.safetensors +++ b/model-00026-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:09142d56351004de8c8a6aa92cf119528bba87e5099e943b07bc5d35d8524e49 -size 4467371896 +oid sha256:a06f375b49a832da777126b930b60e7320445692d6b70d0905885a9326e4da76 +size 4463442560 diff --git a/model-00027-of-00059.safetensors b/model-00027-of-00059.safetensors index a152aad15548dc82f09e029f8639d9162fbd8112..3572dc3a5de03c2262fb74d4a269abf8204cd298 100644 --- a/model-00027-of-00059.safetensors +++ b/model-00027-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b7ca9b1ea954ac2d4a29fb3a6382e7238fc2fca906eabc715070825cc3dfe8ec -size 3998620616 +oid sha256:a3550bbbfcada827aa265bca57d1de8f6d0b7965c27939bd952939700a9de2e7 +size 3994691280 diff --git a/model-00028-of-00059.safetensors b/model-00028-of-00059.safetensors index 41ffca786b49c9cdd03bf72ff53462739a42847f..3ac5cba0ce7ba9bd97971b81188e82b5e98b8bd4 100644 --- a/model-00028-of-00059.safetensors +++ b/model-00028-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9608af604ab814b9c0c884d18015c18bd4b66a89c037222751a2c36aafc9974a -size 3998620616 +oid sha256:6ca9f10ad0d2ad90e97930bf84c348342ae25ddf85bf8014c28afc2b14400f78 +size 3994691280 diff --git a/model-00029-of-00059.safetensors b/model-00029-of-00059.safetensors index cfe99881840520e41535dff18d1c294e09a31898..031f32a93d7c162705cf6fc960e6c953fa90e4dc 100644 --- a/model-00029-of-00059.safetensors +++ b/model-00029-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:458c063d32454a2191c3840ac51497b2887e7bd4d4c52ffdc81e30af98d7184d -size 3998620616 +oid sha256:ff0479228ca1d3db91294bb48107a4787dda8ee65f40a163a8d577b21b41c4f5 +size 3994691280 diff --git a/model-00030-of-00059.safetensors b/model-00030-of-00059.safetensors index e73133ea22d8e0362e0a09bc2b965cb1756a0f41..7be1594abe5efc0140529d0409f586dfbe434a7f 100644 --- a/model-00030-of-00059.safetensors +++ b/model-00030-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:572de22c9fd14b77720e5a50c4098e4163c5e012f9884aa838504865fe25e8e2 -size 3998620616 +oid sha256:6891271851b125edf756cf8b2b0f0c30bd8d6b4fe52a5cd9d8b51114715d7ecf +size 3994691280 diff --git a/model-00031-of-00059.safetensors b/model-00031-of-00059.safetensors index 8dbab8772d0a8f18844bbe32426283e823770a1f..1e83b9060e7008a0cf9cb8cd78f55d2073202f3f 100644 --- a/model-00031-of-00059.safetensors +++ b/model-00031-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8d881bad3b15816d4477f0a240d3bcdf9a5cb180c6532e2c275d5aad1ece17ca -size 3998620616 +oid sha256:c83d0dc28bf4be1d563aa362ce5a61a4da585f8b6a21fe486eec19db5588d533 +size 3994691280 diff --git a/model-00032-of-00059.safetensors b/model-00032-of-00059.safetensors index 5ac9406d523980e4a3936e26c8debc1c05b3949f..4a6b82875ef31ab75adf72c2e317b9b7097161a2 100644 --- a/model-00032-of-00059.safetensors +++ b/model-00032-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1b43e5f029e66a41e86fec9f4906c9a8f9dccedd52c9e58e7cd0750f920b4847 -size 3998620616 +oid sha256:ad84178fe8cec77cffecc6d7e7454d8402fc64536bd0975f89db5cef5aab786a +size 3994691280 diff --git a/model-00033-of-00059.safetensors b/model-00033-of-00059.safetensors index 38833298d7aceead720bfe1967d7919d8700e16a..1ea75b9bf730398d9b522233e786fd32e28c5b0d 100644 --- a/model-00033-of-00059.safetensors +++ b/model-00033-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8b1ee30f5b9f9d44ebc3a96ad7f0a6499bd56c11b22c725c3f281f455a2e77e0 -size 3998620616 +oid sha256:59be31958ff479ef40f6528ec282072bbe6df07c458040d4961810d06170b006 +size 3994691280 diff --git a/model-00034-of-00059.safetensors b/model-00034-of-00059.safetensors index c9ddfd2a9d011de4a51a2537987721d97041ed1f..3ebb1a1fd532aa734469f824181e9f5b1910b9b1 100644 --- a/model-00034-of-00059.safetensors +++ b/model-00034-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ce5a51cd9f8d2067c42f5f7d47d55789e93808a2176ffa7ea18e6ac596257e43 -size 3998620616 +oid sha256:6704ccab30a79faad151e3716990d3772892126d238072b8648be3ed5f4ea844 +size 3994691280 diff --git a/model-00035-of-00059.safetensors b/model-00035-of-00059.safetensors index d587e88b1cc12870f7ba382d34fe892ed08067fb..c18977b90d3619044dc3e0067cbf09fb75c2bcce 100644 --- a/model-00035-of-00059.safetensors +++ b/model-00035-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fefeeb95b893cc427d3f4cacdc7ed31b1b38a2fde920beccf2514290998ea0e5 -size 3998620616 +oid sha256:100436d8f1c228be17f218dae892a3a60494663b64eb71e8bdfc02fbe8446b8f +size 3994691280 diff --git a/model-00036-of-00059.safetensors b/model-00036-of-00059.safetensors index acea68eaac201274167c113ebdf75034d99a107b..c189f9e5991c8072d059de9893cedc62bf9b90cb 100644 --- a/model-00036-of-00059.safetensors +++ b/model-00036-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:efb405abb4c5dfe237f6f3abbd1f426a67111668aa0062a2ca28b3aa6837b37d -size 3998620616 +oid sha256:6d5f30f3fb8bfd7a53f3bcfea61e764a77879d214ce51f27ffa804b6f25abadb +size 3994691280 diff --git a/model-00037-of-00059.safetensors b/model-00037-of-00059.safetensors index 5bf6c15e1bae7d7f470cb3b9ae804cb5f36c302f..746af450112b2f9d5d5ffb4aedfe019fa9c4eba7 100644 --- a/model-00037-of-00059.safetensors +++ b/model-00037-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:628a8c33eedc319672954309a46e71e04a4fa039211029ba03fd6abe2069ca21 -size 3667718952 +oid sha256:f7b6c29e0e21a6606701cfbecd1d86d2e1e897d4240f0cefcef0ac2a2fdab759 +size 3663789616 diff --git a/model-00038-of-00059.safetensors b/model-00038-of-00059.safetensors index 386cd8c60cfc9ccde58bf7e7a2fe3b367d890ead..e94aff728ca40f26f501cbbd910232f96ea9ad6e 100644 --- a/model-00038-of-00059.safetensors +++ b/model-00038-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0c9518f30f722a3a1ed4c3fe7685daf7eea46ec8d69d06e3f952526c57d0164e -size 3667718952 +oid sha256:6269388ea6c860bac35be360ae3d51df282d5927942f072c1baa105ca7713758 +size 3663789616 diff --git a/model-00039-of-00059.safetensors b/model-00039-of-00059.safetensors index b331460ce7dc78c41ea786352a0de132f3c75e1d..b513313d8f7384fcf2ee0d7dce1e0f0d734b0c47 100644 --- a/model-00039-of-00059.safetensors +++ b/model-00039-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5d0b43cba4acefc5439829394fe765be79d48317c4a0b62959e150f832283c77 -size 3667718952 +oid sha256:8fa39d118cede26107338f256ebb07dda4aadce79607d0ef766d66d4636c2946 +size 3663789616 diff --git a/model-00040-of-00059.safetensors b/model-00040-of-00059.safetensors index 9a6fc9165d8b34854b8ae00fa67e221d4f05a430..f109629b948a0a008cea375895cead175fb57ba7 100644 --- a/model-00040-of-00059.safetensors +++ b/model-00040-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5e40a29d4a86a89d372332ec89534217261fdad28dcaf189c02fcc356e6cfae8 -size 3667718952 +oid sha256:3aa857db4d018a49342d62d94a9329c9abd513c48dd23c450139d5fa13fdcb17 +size 3663789616 diff --git a/model-00041-of-00059.safetensors b/model-00041-of-00059.safetensors index 8feeba0b0ef24456a95ea99c7e55bd81da6c74be..36c93ca32a9d2c3495a39c51c500a5214e555dbb 100644 --- a/model-00041-of-00059.safetensors +++ b/model-00041-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fdf3bdd056c209e7366f4dea946766d05d0d3261fff1091706993267cc17911a -size 3667718952 +oid sha256:4ba983919827eb2d71c935be25af68508ae320ff77660c225dcab401e878106c +size 3663789616 diff --git a/model-00042-of-00059.safetensors b/model-00042-of-00059.safetensors index efb2dc60b578a44401394e746f1c99e55df8804e..c016771f1b04740f13024e86c3edf585b4aa0966 100644 --- a/model-00042-of-00059.safetensors +++ b/model-00042-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dfc8548bd368f1460a1d3d9d3c0a55dfca97a062c6419e870711f2b314658306 -size 3667718952 +oid sha256:a329a325cb8a092fd89a0f902aefc8c06d0d46df8f839de2d7935fe06c48c7b8 +size 3663789616 diff --git a/model-00043-of-00059.safetensors b/model-00043-of-00059.safetensors index f042e9350511f971668d3c823a30b1bb641d07c7..f3d29ad920f5deae0382d0b91eaa85d9cf8d3e16 100644 --- a/model-00043-of-00059.safetensors +++ b/model-00043-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b6b9fa24e5b0571412c9549c607c8bfcbb7f86246dc943d6b53cec7e5d2f583c -size 3667718952 +oid sha256:c7ea7db06a1d7d92bd774aae395a98003a7b871b8bf75e6cb0b6c5847994cf5c +size 3663789616 diff --git a/model-00044-of-00059.safetensors b/model-00044-of-00059.safetensors index 2ce6d51d25f87e927dfb2ca6b93d218d372312dd..7f6b1ed4f78ce27983117fe286ed9b7448adbfd7 100644 --- a/model-00044-of-00059.safetensors +++ b/model-00044-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6228790f49431f184a104dbd13fd1895c679b72e58baef55abfd94b5db4d6ca5 -size 3667718952 +oid sha256:48d0b38b7dfad546c733723e408580023196a09949918806eb614f15ca210869 +size 3663789616 diff --git a/model-00045-of-00059.safetensors b/model-00045-of-00059.safetensors index 126bfb33f6e2a6c17b657bed4977f71b6ec057e3..8c26c68122b66c5329a9044d9014489044adccb3 100644 --- a/model-00045-of-00059.safetensors +++ b/model-00045-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7420a4fdfcba1383f140dfe75c8ab68325f1cd2d936a8d6f1cea982b5b7b2934 -size 3667718952 +oid sha256:523c8d336b1437c1eab4ad00a8dff806f2c538cb47c60b258732df84667d9da0 +size 3663789616 diff --git a/model-00046-of-00059.safetensors b/model-00046-of-00059.safetensors index bb2cc1b68c2aeeb5ce1c973a963a916bbd7e8917..c37ba2aaf6ce21719cca44a45c3fcb946f61019c 100644 --- a/model-00046-of-00059.safetensors +++ b/model-00046-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3b27953a5e2102a2dd094daea66ea3dcd4c0f55e475a3fb4a2051a5903ec6a1e -size 3667718952 +oid sha256:cbeaa13cd3a6e5c5c1776d3825b409418354a00b0446cc84eec49d5208e7ec37 +size 3663789616 diff --git a/model-00047-of-00059.safetensors b/model-00047-of-00059.safetensors index 82240ad0900169318bd9f2dbf8dc4a093c6b848a..3c6e762be941342c26f9f64ed5ef76fef7c0f091 100644 --- a/model-00047-of-00059.safetensors +++ b/model-00047-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:993fefc419ed99a9a9526ecbff089192be95239b60763897f54a545306058132 -size 3667718952 +oid sha256:332de26e3f3fbc9e4d130710f4f1faba20c272cef0ef0a67545943c3a86a6ad1 +size 3663789616 diff --git a/model-00048-of-00059.safetensors b/model-00048-of-00059.safetensors index cb626eaedd9421735779a9e8733bc3980f4e9855..4a30aca4977f844504e0d9e497f1de5bf16c719f 100644 --- a/model-00048-of-00059.safetensors +++ b/model-00048-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:785570769db438540d0a32fa572fbfee8cb5368b63d84c7c6aa64a6e5916d3bb -size 3667718952 +oid sha256:8751d01625f011d0f47eb2eef99b453e394fe44f458d49be7282cbe0624e711f +size 3663789616 diff --git a/model-00049-of-00059.safetensors b/model-00049-of-00059.safetensors index 1c2b9754929f854ecb3d44d17451a171bf60e0ca..e50a882397bac6f5af10de1d4e0fc49a16a6a1e9 100644 --- a/model-00049-of-00059.safetensors +++ b/model-00049-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb28fea14f72f2546c48cada465592cdd2fc82f6e8b40fd208150f7a948d22a2 -size 3667718952 +oid sha256:00315f20cd2ef241501956e0ba7b523159612b86cfb8a19bff185bbe6e00a9fb +size 3663789616 diff --git a/model-00050-of-00059.safetensors b/model-00050-of-00059.safetensors index 5a91424763b922ff68284cbca477f84f47679856..a618490caca8c8dd1b5c8a91263b9d43b2da133a 100644 --- a/model-00050-of-00059.safetensors +++ b/model-00050-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b28ba97ce6ffac492911b513f60263771947ae299d3e296701c0ac0bcc00d0d5 -size 3667718952 +oid sha256:d103120af7b5e2efb9589c81f397b6442beadced17933c829cb7f28991db40bc +size 3663789616 diff --git a/model-00051-of-00059.safetensors b/model-00051-of-00059.safetensors index b94fa2015122804aeeec19b7f492f08c5f23d4f6..f0046f61029eea20062b38f2f04ec4caa3883a4a 100644 --- a/model-00051-of-00059.safetensors +++ b/model-00051-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:227f1af3fc00c1cb7ac327075895c0caf9a34dead3432810a7dc434f08fdd28a -size 3667718952 +oid sha256:8468a113cc75e9d42146031730cc2763cd5a2baf8d5281a5c3f4dbd9066d9e6b +size 3663789616 diff --git a/model-00052-of-00059.safetensors b/model-00052-of-00059.safetensors index 86a6adcf00f076a7fe7032c042e23ac36b718058..46282918e4833c4666ba2378d201f7af5e6d4acd 100644 --- a/model-00052-of-00059.safetensors +++ b/model-00052-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:996c6f689496f014993d06db0c363d416e8c793f1d458f138fb1d6aadad5e41b -size 3667718952 +oid sha256:b6f8cd5c467f529e8aca2a3db5f4d9907e6858084f95e7b1e9f3871a6a2e0ffa +size 3663789616 diff --git a/model-00053-of-00059.safetensors b/model-00053-of-00059.safetensors index 0f0f380f124b10ba14afbe98346890865b8da6ba..0c1a1ea4fcbec874dd5b89dc7768a1a4c6226407 100644 --- a/model-00053-of-00059.safetensors +++ b/model-00053-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fae755b17f0c6a6bbe4aeda5081664e5aaff6bc51265006304036776b06197b2 -size 3667718952 +oid sha256:c4ebe38ec7d8d0cdbe1beebe2d30e3ae0e0e55e4242025690b739f9b7d336bdb +size 3663789616 diff --git a/model-00054-of-00059.safetensors b/model-00054-of-00059.safetensors index 66383aeb3e0e826ee9b4b13367dbac9ca1db45c6..dd91eab42f9f02e622bf8e6dc484a3dc53f332db 100644 --- a/model-00054-of-00059.safetensors +++ b/model-00054-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:952e89c5a9aab145fe45f5736768f18a4204dcef29dc95639ec76d771433a055 -size 3667718952 +oid sha256:7a51030a327611c2513f8a5014461150f8ed1a6e82a98c82a07ca888b708f242 +size 3663789616 diff --git a/model-00055-of-00059.safetensors b/model-00055-of-00059.safetensors index 7c913da602790b65c65624813b667a4d2b4a00ec..223302980a75ae849349b3ebcdd18b92d42c4d97 100644 --- a/model-00055-of-00059.safetensors +++ b/model-00055-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:564dc78152b674d931c71516081fae6b03c432130930890f779832b686714a1c -size 3667718952 +oid sha256:cee2cb9a32282f4eae3d0c4b96c812fd933eff0946235116b4c46fc5738ee92f +size 3663789616 diff --git a/model-00056-of-00059.safetensors b/model-00056-of-00059.safetensors index 1f1f2e7e23962edd3df5cec86378ef64836197d0..d946964d86971b83108ed5162ccbcaad7fd4a443 100644 --- a/model-00056-of-00059.safetensors +++ b/model-00056-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:addcee6574305dba726c8b9d77d3bb07ec97d4a38b56fcc5558ea8dafcb743c0 -size 3667718952 +oid sha256:339ddaceeb228b027b3af8316148fbb780fac1fd98c0f1ec45372cb273dc4bf7 +size 3663789616 diff --git a/model-00057-of-00059.safetensors b/model-00057-of-00059.safetensors index 799cc86fb11dc5c1aca1a8dba65536bcbf51e84b..11f83f2e3c0670343bc1b5928c61e5790b6786fb 100644 --- a/model-00057-of-00059.safetensors +++ b/model-00057-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cc687e8eb16770545dfb6060b50093c00ee0a9e30d933fd33b731ebced7ea63b -size 3667718952 +oid sha256:795680f1accb2c7a335e99507e90c86f5ca2b5b4ab50e355d1072323e9d37beb +size 3663789616 diff --git a/model-00058-of-00059.safetensors b/model-00058-of-00059.safetensors index 9e43e2ccb70bdbd20db02996943d1040fe609c15..83c014b8d94ad1d3be01eac2576700eb4718e2a5 100644 --- a/model-00058-of-00059.safetensors +++ b/model-00058-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bd95160949de1402d374bddd4c9a2bcd9b115da82b6bc59236ed88aad1bd78ed -size 3667718952 +oid sha256:2170d1cc4bc156b8f29d89025d8bdf059244615fa82603e9fc1d2a71d2ee1dda +size 3663789616 diff --git a/model-00059-of-00059.safetensors b/model-00059-of-00059.safetensors index 500eb16c95f534ac5b5572270823ef30cf486350..16a970675a586aaea125e84f3aca843964d62a25 100644 --- a/model-00059-of-00059.safetensors +++ b/model-00059-of-00059.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2bb2660492b0451512a522e06846f1f9fbc9568a3879bddf70f16973f5fa29da -size 5264086096 +oid sha256:aa8d044fb9d2819be5d0777f9c4378c0cac282ea82ab0f5732f8a1dfb5aadffe +size 5260156744 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index 7413c22a33d133adcae8d4f88206eb3ee107ffae..2b3f9b1c9b8bd4f4cedbdbb785bbea22e44bf7ad 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -1,44424 +1,3068 @@ { "metadata": { - "total_size": 235254474888 + "total_size": 236028483864 }, "weight_map": { - "language_model.model.layers.48.block_sparse_moe.gate.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.108.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.108.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.108.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.108.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.108.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.108.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.109.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.109.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.109.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.109.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.109.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.109.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.11.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.11.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.11.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.11.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.11.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.11.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.110.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.110.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.110.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.110.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.110.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.110.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.111.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.111.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.111.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.111.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.111.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.111.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.112.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.112.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.112.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.112.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.112.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.112.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.113.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.113.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.113.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.113.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.113.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.113.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.114.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.114.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.114.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.114.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.114.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.114.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.115.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.115.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.115.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.115.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.115.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.115.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.116.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.116.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.116.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.116.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.116.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.116.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.117.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.117.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.117.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.117.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.117.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.117.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.118.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.118.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.118.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.118.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.118.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.118.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.119.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.119.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.119.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.119.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.119.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.119.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.12.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.12.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.12.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.12.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.12.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.12.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.120.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.120.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.120.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.120.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.120.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.120.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.121.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.121.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.121.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.121.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.121.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.121.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.122.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.122.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.122.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.122.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.122.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.122.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.123.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.123.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.123.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.123.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.123.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.123.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.124.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.124.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.124.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.124.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.124.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.124.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.125.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.125.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.125.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.125.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.125.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.125.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.126.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.126.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.126.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.126.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.126.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.126.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.127.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.127.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.127.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.127.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.127.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.127.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.13.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.13.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.13.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.13.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.13.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.13.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.14.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.14.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.14.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.14.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.14.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.14.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.15.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.15.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.15.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.15.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.15.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.15.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.16.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.16.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.16.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.16.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.16.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.16.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.17.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.17.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.17.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.17.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.17.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.17.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.18.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.18.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.18.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.18.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.18.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.18.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.19.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.19.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.19.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.19.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.19.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.19.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.2.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.2.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.2.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.20.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.20.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.20.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.20.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.20.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.20.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.21.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.21.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.21.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.21.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.21.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.21.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.22.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.22.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.22.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.22.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.22.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.22.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.23.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.23.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.23.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.23.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.23.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.23.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.24.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.24.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.24.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.24.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.24.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.24.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.25.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.25.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.25.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.25.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.25.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.25.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.26.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.26.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.26.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.26.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.26.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.26.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.27.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.27.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.27.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.27.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.27.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.27.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.28.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.28.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.28.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.28.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.28.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.28.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.29.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.29.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.29.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.29.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.29.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.29.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.3.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.3.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.3.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.3.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.3.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.3.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.30.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.30.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.30.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.30.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.30.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.30.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.31.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.31.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.31.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.31.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.31.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.31.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.32.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.32.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.32.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.32.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.32.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.32.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.33.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.33.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.33.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.33.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.33.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.33.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.34.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.34.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.34.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.34.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.34.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.34.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.35.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.35.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.35.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.35.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.35.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.35.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.36.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.36.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.36.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.36.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.36.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.36.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.37.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.37.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.37.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.37.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.37.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.37.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.38.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.38.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.38.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.38.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.38.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.38.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.39.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.39.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.39.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.39.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.39.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.39.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.4.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.4.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.4.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.4.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.4.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.4.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.40.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.40.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.40.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.40.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.40.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.40.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.41.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.41.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.41.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.41.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.41.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.41.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.42.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.42.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.42.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.42.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.42.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.42.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.43.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.43.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.43.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.43.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.43.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.43.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.44.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.44.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.44.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.44.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.44.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.44.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.45.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.45.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.45.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.45.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.45.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.45.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.46.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.46.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.46.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.46.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.46.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.46.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.47.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.47.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.47.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.47.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.47.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.47.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.48.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.48.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.48.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.48.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.48.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.48.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.49.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.49.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.49.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.49.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.49.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.49.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.5.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.5.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.5.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.5.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.5.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.5.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.50.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.50.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.50.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.50.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.50.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.50.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.51.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.51.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.51.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.51.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.51.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.51.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.52.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.52.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.52.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.52.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.52.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.52.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.53.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.53.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.53.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.53.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.53.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.53.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.54.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.54.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.54.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.54.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.54.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.54.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.55.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.55.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.55.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.55.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.55.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.55.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.56.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.56.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.56.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.56.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.56.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.56.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.57.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.57.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.57.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.57.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.57.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.57.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.58.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.58.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.58.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.58.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.58.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.58.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.59.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.59.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.59.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.59.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.59.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.59.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.6.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.6.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.6.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.6.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.6.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.6.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.60.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.60.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.60.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.60.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.60.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.60.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.61.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.61.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.61.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.61.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.61.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.61.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.62.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.62.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.62.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.62.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.62.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.62.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.63.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.63.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.63.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.63.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.63.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.63.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.64.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.64.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.64.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.64.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.64.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.64.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.65.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.65.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.65.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.65.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.65.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.65.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.66.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.66.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.66.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.66.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.66.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.66.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.67.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.67.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.67.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.67.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.67.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.67.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.68.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.68.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.68.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.68.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.68.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.68.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.69.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.69.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.69.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.69.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.69.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.69.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.7.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.7.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.7.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.7.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.7.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.7.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.70.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.70.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.70.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.70.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.70.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.70.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.71.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.71.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.71.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.71.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.71.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.71.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.72.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.72.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.72.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.72.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.72.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.72.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.73.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.73.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.73.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.73.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.73.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.73.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.74.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.74.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.74.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.74.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.74.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.74.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.75.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.75.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.75.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.75.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.75.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.75.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.76.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.76.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.76.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.76.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.76.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.76.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.77.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.77.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.77.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.77.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.77.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.77.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.78.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.78.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.78.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.78.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.78.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.78.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.79.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.79.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.79.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.79.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.79.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.79.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.8.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.8.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.8.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.8.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.8.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.8.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.80.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.80.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.80.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.80.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.80.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.80.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.81.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.81.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.81.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.81.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.81.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.81.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.82.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.82.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.82.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.82.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.82.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.82.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.83.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.83.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.83.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.83.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.83.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.83.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.84.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.84.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.84.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.84.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.84.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.84.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.85.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.85.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.85.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.85.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.85.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.85.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.86.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.86.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.86.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.86.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.86.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.86.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.87.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.87.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.87.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.87.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.87.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.87.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.88.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.88.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.88.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.88.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.88.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.88.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.89.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.89.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.89.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.89.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.89.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.89.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.9.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.9.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.9.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.9.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.9.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.9.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.90.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.90.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.90.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.90.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.90.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.90.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.91.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.91.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.91.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.91.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.91.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.91.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.92.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.92.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.92.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.92.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.92.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.92.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.93.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.93.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.93.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.93.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.93.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.93.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.94.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.94.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.94.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.94.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.94.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.94.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.95.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.95.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.95.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.95.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.95.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.95.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.96.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.96.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.96.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.96.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.96.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.96.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.97.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.97.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.97.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.97.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.97.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.97.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.98.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.98.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.98.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.98.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.98.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.98.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.99.w1.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.99.w1.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.99.w2.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.99.w2.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.99.w3.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.99.w3.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.shared_experts.down_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.shared_experts.gate_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.shared_experts.up_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.input_layernorm.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.post_attention_layernorm.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.index_k_norm.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.index_k_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.index_q_norm.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.index_q_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.k_norm.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.k_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.k_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.o_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.o_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.q_norm.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.q_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.q_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.v_proj.weight": "model-00048-of-00059.safetensors", - "language_model.model.layers.48.self_attn.v_proj.weight_scale": "model-00048-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.gate.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.108.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.108.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.108.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.108.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.108.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.108.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.109.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.109.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.109.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.109.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.109.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.109.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.11.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.11.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.11.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.11.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.11.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.11.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.110.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.110.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.110.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.110.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.110.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.110.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.111.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.111.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.111.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.111.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.111.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.111.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.112.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.112.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.112.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.112.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.112.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.112.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.113.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.113.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.113.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.113.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.113.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.113.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.114.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.114.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.114.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.114.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.114.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.114.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.115.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.115.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.115.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.115.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.115.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.115.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.116.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.116.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.116.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.116.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.116.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.116.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.117.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.117.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.117.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.117.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.117.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.117.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.118.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.118.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.118.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.118.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.118.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.118.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.119.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.119.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.119.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.119.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.119.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.119.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.12.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.12.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.12.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.12.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.12.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.12.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.120.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.120.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.120.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.120.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.120.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.120.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.121.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.121.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.121.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.121.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.121.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.121.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.122.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.122.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.122.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.122.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.122.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.122.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.123.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.123.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.123.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.123.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.123.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.123.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.124.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.124.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.124.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.124.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.124.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.124.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.125.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.125.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.125.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.125.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.125.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.125.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.126.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.126.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.126.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.126.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.126.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.126.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.127.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.127.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.127.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.127.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.127.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.127.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.13.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.13.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.13.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.13.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.13.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.13.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.14.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.14.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.14.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.14.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.14.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.14.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.15.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.15.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.15.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.15.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.15.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.15.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.16.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.16.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.16.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.16.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.16.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.16.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.17.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.17.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.17.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.17.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.17.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.17.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.18.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.18.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.18.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.18.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.18.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.18.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.19.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.19.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.19.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.19.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.19.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.19.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.2.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.2.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.2.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.20.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.20.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.20.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.20.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.20.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.20.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.21.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.21.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.21.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.21.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.21.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.21.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.22.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.22.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.22.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.22.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.22.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.22.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.23.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.23.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.23.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.23.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.23.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.23.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.24.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.24.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.24.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.24.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.24.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.24.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.25.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.25.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.25.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.25.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.25.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.25.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.26.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.26.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.26.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.26.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.26.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.26.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.27.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.27.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.27.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.27.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.27.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.27.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.28.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.28.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.28.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.28.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.28.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.28.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.29.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.29.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.29.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.29.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.29.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.29.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.3.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.3.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.3.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.30.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.30.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.30.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.30.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.30.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.30.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.31.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.31.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.31.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.31.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.31.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.31.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.32.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.32.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.32.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.32.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.32.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.32.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.33.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.33.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.33.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.33.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.33.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.33.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.34.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.34.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.34.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.34.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.34.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.34.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.35.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.35.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.35.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.35.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.35.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.35.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.36.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.36.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.36.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.36.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.36.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.36.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.37.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.37.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.37.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.37.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.37.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.37.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.38.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.38.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.38.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.38.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.38.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.38.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.39.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.39.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.39.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.39.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.39.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.39.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.4.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.4.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.4.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.4.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.4.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.4.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.40.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.40.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.40.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.40.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.40.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.40.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.41.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.41.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.41.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.41.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.41.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.41.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.42.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.42.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.42.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.42.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.42.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.42.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.43.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.43.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.43.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.43.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.43.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.43.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.44.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.44.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.44.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.44.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.44.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.44.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.45.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.45.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.45.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.45.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.45.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.45.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.46.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.46.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.46.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.46.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.46.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.46.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.47.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.47.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.47.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.47.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.47.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.47.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.48.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.48.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.48.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.48.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.48.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.48.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.49.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.49.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.49.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.49.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.49.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.49.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.5.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.5.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.5.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.50.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.50.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.50.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.50.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.50.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.50.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.51.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.51.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.51.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.51.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.51.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.51.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.52.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.52.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.52.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.52.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.52.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.52.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.53.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.53.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.53.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.53.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.53.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.53.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.54.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.54.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.54.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.54.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.54.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.54.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.55.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.55.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.55.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.55.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.55.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.55.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.56.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.56.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.56.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.56.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.56.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.56.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.57.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.57.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.57.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.57.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.57.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.57.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.58.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.58.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.58.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.58.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.58.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.58.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.59.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.59.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.59.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.59.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.59.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.59.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.6.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.6.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.6.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.60.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.60.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.60.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.60.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.60.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.60.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.61.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.61.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.61.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.61.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.61.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.61.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.62.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.62.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.62.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.62.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.62.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.62.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.63.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.63.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.63.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.63.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.63.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.63.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.64.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.64.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.64.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.64.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.64.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.64.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.65.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.65.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.65.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.65.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.65.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.65.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.66.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.66.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.66.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.66.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.66.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.66.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.67.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.67.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.67.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.67.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.67.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.67.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.68.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.68.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.68.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.68.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.68.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.68.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.69.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.69.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.69.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.69.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.69.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.69.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.7.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.7.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.7.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.70.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.70.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.70.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.70.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.70.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.70.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.71.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.71.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.71.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.71.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.71.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.71.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.72.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.72.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.72.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.72.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.72.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.72.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.73.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.73.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.73.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.73.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.73.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.73.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.74.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.74.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.74.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.74.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.74.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.74.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.75.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.75.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.75.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.75.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.75.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.75.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.76.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.76.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.76.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.76.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.76.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.76.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.77.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.77.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.77.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.77.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.77.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.77.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.78.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.78.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.78.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.78.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.78.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.78.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.79.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.79.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.79.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.79.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.79.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.79.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.8.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.8.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.8.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.8.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.8.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.8.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.80.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.80.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.80.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.80.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.80.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.80.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.81.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.81.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.81.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.81.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.81.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.81.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.82.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.82.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.82.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.82.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.82.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.82.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.83.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.83.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.83.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.83.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.83.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.83.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.84.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.84.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.84.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.84.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.84.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.84.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.85.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.85.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.85.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.85.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.85.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.85.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.86.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.86.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.86.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.86.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.86.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.86.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.87.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.87.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.87.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.87.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.87.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.87.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.88.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.88.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.88.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.88.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.88.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.88.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.89.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.89.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.89.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.89.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.89.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.89.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.9.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.9.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.9.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.9.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.9.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.9.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.90.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.90.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.90.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.90.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.90.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.90.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.91.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.91.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.91.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.91.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.91.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.91.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.92.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.92.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.92.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.92.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.92.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.92.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.93.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.93.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.93.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.93.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.93.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.93.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.94.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.94.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.94.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.94.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.94.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.94.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.95.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.95.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.95.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.95.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.95.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.95.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.96.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.96.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.96.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.96.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.96.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.96.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.97.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.97.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.97.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.97.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.97.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.97.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.98.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.98.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.98.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.98.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.98.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.98.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.99.w1.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.99.w1.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.99.w2.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.99.w2.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.99.w3.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.99.w3.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.shared_experts.down_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.shared_experts.gate_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.shared_experts.up_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.input_layernorm.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.post_attention_layernorm.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.index_k_norm.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.index_k_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.index_q_norm.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.index_q_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.k_norm.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.k_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.k_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.o_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.o_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.q_norm.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.q_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.q_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.v_proj.weight": "model-00040-of-00059.safetensors", - "language_model.model.layers.40.self_attn.v_proj.weight_scale": "model-00040-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.e_score_correction_bias": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.e_score_correction_bias": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.0.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.0.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.0.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.1.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.1.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.1.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.10.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.10.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.10.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.100.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.100.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.100.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.101.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.101.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.101.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.102.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.102.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.102.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.103.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.103.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.103.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.104.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.104.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.104.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.105.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.105.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.105.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.106.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.106.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.106.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.107.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.107.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.107.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.108.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.108.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.108.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.108.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.108.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.108.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.109.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.109.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.109.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.109.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.109.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.109.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.11.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.11.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.11.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.110.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.110.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.110.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.110.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.110.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.110.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.111.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.111.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.111.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.111.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.111.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.111.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.112.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.112.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.112.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.112.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.112.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.112.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.113.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.113.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.113.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.113.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.113.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.113.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.114.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.114.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.114.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.114.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.114.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.114.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.115.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.115.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.115.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.115.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.115.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.115.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.116.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.116.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.116.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.116.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.116.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.116.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.117.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.117.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.117.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.117.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.117.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.117.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.118.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.118.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.118.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.118.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.118.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.118.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.119.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.119.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.119.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.119.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.119.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.119.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.12.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.12.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.12.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.120.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.120.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.120.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.120.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.120.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.120.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.121.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.121.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.121.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.121.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.121.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.121.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.122.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.122.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.122.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.122.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.122.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.122.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.123.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.123.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.123.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.123.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.123.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.123.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.124.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.124.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.124.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.124.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.124.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.124.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.125.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.125.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.125.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.125.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.125.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.125.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.126.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.126.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.126.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.126.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.126.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.126.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.127.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.127.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.127.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.127.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.127.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.127.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.13.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.13.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.13.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.14.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.14.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.14.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.15.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.15.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.15.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.16.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.16.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.16.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.17.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.17.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.17.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.18.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.18.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.18.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.19.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.19.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.19.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.2.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.2.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.2.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.20.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.20.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.20.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.21.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.21.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.21.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.22.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.22.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.22.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.23.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.23.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.23.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.24.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.24.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.24.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.25.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.25.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.25.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.26.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.26.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.26.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.27.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.27.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.27.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.28.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.28.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.28.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.29.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.29.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.29.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.3.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.3.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.3.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.30.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.30.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.30.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.31.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.31.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.31.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.32.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.32.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.32.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.32.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.32.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.32.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.33.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.33.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.33.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.33.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.33.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.33.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.34.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.34.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.34.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.34.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.34.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.34.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.35.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.35.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.35.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.35.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.35.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.35.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.36.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.36.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.36.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.36.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.36.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.36.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.37.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.37.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.37.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.37.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.37.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.37.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.38.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.38.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.38.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.38.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.38.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.38.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.39.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.39.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.39.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.39.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.39.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.39.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.4.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.4.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.4.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.40.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.40.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.40.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.40.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.40.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.40.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.41.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.41.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.41.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.41.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.41.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.41.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.42.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.42.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.42.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.42.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.42.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.42.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.43.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.43.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.43.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.43.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.43.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.43.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.44.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.44.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.44.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.44.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.44.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.44.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.45.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.45.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.45.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.45.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.45.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.45.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.46.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.46.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.46.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.46.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.46.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.46.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.47.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.47.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.47.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.47.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.47.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.47.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.48.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.48.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.48.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.48.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.48.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.48.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.49.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.49.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.49.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.49.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.49.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.49.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.5.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.5.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.5.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.50.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.50.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.50.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.50.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.50.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.50.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.51.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.51.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.51.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.51.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.51.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.51.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.52.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.52.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.52.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.52.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.52.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.52.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.53.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.53.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.53.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.53.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.53.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.53.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.54.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.54.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.54.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.54.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.54.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.54.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.55.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.55.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.55.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.55.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.55.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.55.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.56.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.56.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.56.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.56.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.56.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.56.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.57.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.57.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.57.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.57.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.57.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.57.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.58.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.58.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.58.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.58.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.58.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.58.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.59.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.59.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.59.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.59.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.59.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.59.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.6.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.6.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.6.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.60.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.60.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.60.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.60.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.60.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.60.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.61.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.61.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.61.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.61.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.61.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.61.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.62.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.62.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.62.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.62.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.62.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.62.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.63.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.63.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.63.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.63.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.63.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.63.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.64.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.64.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.64.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.64.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.64.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.64.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.65.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.65.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.65.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.65.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.65.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.65.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.66.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.66.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.66.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.66.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.66.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.66.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.67.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.67.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.67.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.67.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.67.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.67.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.68.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.68.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.68.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.68.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.68.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.68.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.69.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.69.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.69.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.69.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.69.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.69.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.7.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.7.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.7.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.70.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.70.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.70.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.70.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.70.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.70.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.71.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.71.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.71.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.71.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.71.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.71.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.72.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.72.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.72.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.72.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.72.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.72.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.73.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.73.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.73.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.73.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.73.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.73.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.74.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.74.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.74.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.74.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.74.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.74.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.75.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.75.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.75.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.75.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.75.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.75.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.76.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.76.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.76.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.76.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.76.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.76.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.77.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.77.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.77.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.77.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.77.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.77.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.78.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.78.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.78.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.78.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.78.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.78.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.79.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.79.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.79.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.79.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.79.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.79.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.8.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.8.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.8.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.80.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.80.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.80.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.80.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.80.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.80.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.81.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.81.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.81.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.81.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.81.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.81.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.82.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.82.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.82.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.82.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.82.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.82.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.83.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.83.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.83.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.83.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.83.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.83.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.84.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.84.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.84.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.84.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.84.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.84.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.85.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.85.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.85.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.85.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.85.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.85.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.86.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.86.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.86.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.86.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.86.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.86.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.87.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.87.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.87.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.87.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.87.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.87.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.88.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.88.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.88.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.88.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.88.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.88.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.89.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.89.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.89.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.89.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.89.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.89.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.9.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.9.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.9.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.90.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.90.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.90.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.90.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.90.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.90.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.91.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.91.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.91.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.91.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.91.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.91.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.92.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.92.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.92.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.92.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.92.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.92.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.93.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.93.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.93.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.93.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.93.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.93.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.94.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.94.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.94.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.94.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.94.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.94.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.95.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.95.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.95.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.95.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.95.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.95.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.96.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.96.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.96.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.96.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.96.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.96.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.97.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.97.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.97.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.97.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.97.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.97.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.98.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.98.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.98.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.98.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.98.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.98.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.99.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.99.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.99.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.99.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.99.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.experts.99.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.shared_experts.down_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.shared_experts.gate_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.shared_experts.up_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.input_layernorm.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.post_attention_layernorm.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.index_k_norm.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.index_k_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.index_q_norm.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.index_q_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.k_norm.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.k_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.k_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.o_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.o_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.q_norm.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.q_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.q_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.v_proj.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.0.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.0.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.0.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.1.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.1.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.1.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.10.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.10.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.10.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.100.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.100.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.100.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.101.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.101.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.101.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.102.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.102.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.102.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.103.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.103.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.103.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.104.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.104.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.104.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.105.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.105.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.105.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.106.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.106.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.106.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.107.w1.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.107.w2.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.107.w3.weight_scale": "model-00012-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.e_score_correction_bias": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.e_score_correction_bias": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.0.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.0.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.0.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.1.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.1.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.1.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.10.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.10.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.10.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.100.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.100.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.100.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.101.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.101.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.101.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.102.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.102.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.102.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.103.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.103.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.103.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.104.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.104.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.104.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.105.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.105.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.105.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.106.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.106.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.106.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.107.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.107.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.107.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.0.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.0.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.0.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.1.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.1.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.1.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.10.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.10.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.10.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.100.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.100.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.100.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.101.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.101.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.101.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.102.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.102.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.102.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.103.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.103.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.103.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.104.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.104.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.104.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.105.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.105.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.105.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.106.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.106.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.106.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.107.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.107.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.107.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.108.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.108.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.108.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.108.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.108.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.108.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.109.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.109.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.109.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.109.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.109.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.109.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.11.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.11.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.11.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.110.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.110.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.110.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.110.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.110.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.110.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.111.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.111.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.111.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.111.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.111.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.111.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.112.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.112.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.112.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.112.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.112.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.112.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.113.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.113.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.113.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.113.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.113.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.113.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.114.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.114.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.114.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.114.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.114.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.114.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.115.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.115.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.115.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.115.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.115.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.115.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.116.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.116.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.116.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.116.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.116.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.116.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.117.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.117.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.117.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.117.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.117.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.117.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.118.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.118.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.118.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.118.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.118.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.118.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.119.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.119.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.119.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.119.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.119.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.119.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.12.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.12.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.12.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.120.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.120.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.120.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.120.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.120.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.120.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.121.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.121.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.121.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.121.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.121.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.121.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.122.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.122.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.122.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.122.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.122.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.122.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.123.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.123.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.123.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.123.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.123.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.123.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.124.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.124.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.124.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.124.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.124.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.124.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.125.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.125.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.125.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.125.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.125.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.125.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.126.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.126.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.126.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.126.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.126.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.126.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.127.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.127.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.127.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.127.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.127.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.127.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.13.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.13.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.13.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.14.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.14.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.14.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.15.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.15.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.15.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.16.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.16.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.16.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.17.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.17.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.17.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.18.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.18.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.18.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.19.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.19.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.19.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.2.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.2.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.2.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.20.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.20.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.20.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.21.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.21.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.21.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.22.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.22.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.22.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.23.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.23.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.23.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.24.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.24.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.24.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.25.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.25.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.25.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.26.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.26.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.26.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.27.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.27.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.27.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.28.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.28.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.28.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.29.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.29.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.29.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.3.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.3.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.3.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.30.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.30.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.30.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.31.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.31.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.31.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.32.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.32.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.32.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.32.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.32.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.32.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.33.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.33.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.33.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.33.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.33.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.33.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.34.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.34.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.34.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.34.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.34.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.34.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.35.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.35.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.35.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.35.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.35.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.35.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.36.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.36.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.36.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.36.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.36.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.36.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.37.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.37.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.37.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.37.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.37.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.37.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.38.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.38.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.38.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.38.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.38.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.38.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.39.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.39.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.39.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.39.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.39.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.39.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.4.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.4.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.4.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.40.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.40.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.40.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.40.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.40.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.40.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.41.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.41.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.41.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.41.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.41.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.41.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.42.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.42.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.42.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.42.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.42.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.42.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.43.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.43.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.43.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.43.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.43.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.43.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.44.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.44.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.44.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.44.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.44.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.44.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.45.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.45.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.45.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.45.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.45.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.45.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.46.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.46.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.46.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.46.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.46.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.46.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.47.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.47.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.47.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.47.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.47.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.47.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.48.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.48.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.48.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.48.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.48.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.48.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.49.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.49.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.49.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.49.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.49.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.49.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.5.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.5.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.5.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.50.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.50.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.50.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.50.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.50.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.50.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.51.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.51.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.51.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.51.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.51.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.51.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.52.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.52.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.52.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.52.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.52.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.52.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.53.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.53.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.53.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.53.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.53.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.53.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.54.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.54.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.54.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.54.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.54.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.54.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.55.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.55.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.55.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.55.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.55.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.55.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.56.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.56.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.56.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.56.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.56.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.56.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.57.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.57.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.57.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.57.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.57.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.57.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.58.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.58.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.58.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.58.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.58.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.58.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.59.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.59.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.59.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.59.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.59.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.59.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.6.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.6.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.6.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.60.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.60.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.60.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.60.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.60.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.60.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.61.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.61.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.61.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.61.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.61.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.61.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.62.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.62.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.62.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.62.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.62.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.62.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.63.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.63.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.63.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.63.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.63.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.63.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.64.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.64.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.64.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.64.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.64.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.64.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.65.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.65.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.65.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.65.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.65.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.65.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.66.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.66.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.66.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.66.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.66.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.66.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.67.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.67.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.67.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.67.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.67.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.67.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.68.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.68.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.68.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.68.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.68.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.68.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.69.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.69.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.69.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.69.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.69.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.69.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.7.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.7.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.7.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.70.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.70.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.70.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.70.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.70.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.70.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.71.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.71.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.71.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.71.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.71.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.71.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.72.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.72.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.72.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.72.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.72.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.73.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.73.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.73.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.74.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.74.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.74.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.75.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.75.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.75.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.76.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.76.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.76.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.77.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.77.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.77.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.77.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.78.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.78.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.78.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.78.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.78.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.78.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.79.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.79.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.79.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.79.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.79.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.79.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.8.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.8.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.8.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.80.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.80.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.80.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.80.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.80.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.80.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.81.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.81.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.81.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.81.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.81.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.81.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.82.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.82.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.82.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.82.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.82.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.82.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.83.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.83.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.83.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.83.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.83.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.83.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.84.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.84.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.84.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.84.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.84.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.84.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.85.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.85.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.85.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.85.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.85.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.85.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.86.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.86.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.86.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.86.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.86.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.86.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.87.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.87.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.87.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.87.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.87.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.87.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.88.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.88.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.88.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.88.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.88.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.88.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.89.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.89.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.89.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.89.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.89.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.89.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.9.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.9.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.9.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.90.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.90.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.90.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.90.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.90.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.90.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.91.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.91.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.91.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.91.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.91.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.91.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.92.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.92.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.92.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.92.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.92.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.92.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.93.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.93.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.93.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.93.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.93.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.93.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.94.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.94.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.94.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.94.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.94.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.94.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.95.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.95.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.95.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.95.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.95.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.95.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.96.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.96.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.96.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.96.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.96.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.96.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.97.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.97.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.97.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.97.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.97.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.97.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.98.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.98.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.98.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.98.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.98.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.98.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.99.w1.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.99.w1.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.99.w2.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.99.w2.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.99.w3.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.experts.99.w3.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.shared_experts.down_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.shared_experts.gate_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.shared_experts.up_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.input_layernorm.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.post_attention_layernorm.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.index_k_norm.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.index_k_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.index_q_norm.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.index_q_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.k_norm.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.k_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.k_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.o_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.o_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.q_norm.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.q_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.q_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.v_proj.weight": "model-00009-of-00059.safetensors", - "language_model.model.layers.9.self_attn.v_proj.weight_scale": "model-00009-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.e_score_correction_bias": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.e_score_correction_bias": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.0.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.0.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.0.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.1.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.1.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.1.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.10.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.10.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.10.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.100.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.100.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.100.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.101.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.101.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.101.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.102.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.102.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.102.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.103.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.103.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.103.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.104.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.104.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.104.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.105.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.105.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.105.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.106.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.106.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.106.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.107.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.107.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.107.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.0.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.0.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.0.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.1.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.1.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.1.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.10.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.10.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.10.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.100.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.100.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.100.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.101.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.101.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.101.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.102.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.102.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.102.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.103.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.103.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.103.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.104.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.104.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.104.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.105.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.105.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.105.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.106.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.106.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.106.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.107.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.107.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.107.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.108.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.108.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.108.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.108.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.108.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.108.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.109.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.109.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.109.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.109.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.109.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.109.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.11.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.11.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.11.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.110.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.110.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.110.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.110.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.110.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.110.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.111.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.111.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.111.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.111.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.111.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.111.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.112.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.112.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.112.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.112.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.112.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.112.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.113.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.113.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.113.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.113.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.113.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.113.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.114.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.114.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.114.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.114.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.114.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.114.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.115.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.115.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.115.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.115.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.115.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.115.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.116.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.116.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.116.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.116.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.116.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.116.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.117.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.117.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.117.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.117.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.117.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.117.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.118.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.118.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.118.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.118.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.118.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.118.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.119.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.119.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.119.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.119.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.119.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.119.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.12.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.12.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.12.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.120.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.120.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.120.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.120.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.120.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.120.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.121.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.121.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.121.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.121.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.121.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.121.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.122.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.122.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.122.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.122.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.122.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.122.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.123.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.123.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.123.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.123.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.123.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.123.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.124.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.124.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.124.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.124.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.124.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.124.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.125.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.125.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.125.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.125.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.125.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.125.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.126.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.126.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.126.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.126.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.126.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.126.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.127.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.127.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.127.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.127.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.127.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.127.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.13.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.13.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.13.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.14.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.14.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.14.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.15.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.15.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.15.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.16.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.16.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.16.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.17.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.17.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.17.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.18.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.18.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.18.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.19.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.19.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.19.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.2.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.2.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.2.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.20.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.20.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.20.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.21.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.21.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.21.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.22.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.22.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.22.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.23.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.23.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.23.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.24.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.24.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.24.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.25.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.25.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.25.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.26.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.26.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.26.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.27.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.27.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.27.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.28.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.28.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.28.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.29.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.29.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.29.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.3.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.3.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.3.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.30.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.30.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.30.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.31.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.31.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.31.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.32.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.32.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.32.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.32.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.32.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.32.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.33.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.33.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.33.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.33.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.33.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.33.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.34.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.34.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.34.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.34.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.34.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.34.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.35.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.35.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.35.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.35.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.35.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.35.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.36.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.36.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.36.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.36.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.36.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.36.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.37.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.37.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.37.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.37.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.37.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.37.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.38.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.38.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.38.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.38.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.38.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.38.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.39.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.39.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.39.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.39.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.39.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.39.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.4.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.4.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.4.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.40.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.40.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.40.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.40.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.40.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.40.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.41.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.41.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.41.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.41.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.41.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.41.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.42.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.42.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.42.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.42.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.42.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.42.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.43.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.43.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.43.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.43.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.43.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.43.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.44.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.44.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.44.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.44.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.44.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.44.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.45.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.45.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.45.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.45.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.45.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.45.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.46.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.46.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.46.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.46.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.46.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.46.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.47.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.47.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.47.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.47.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.47.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.47.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.48.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.48.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.48.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.48.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.48.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.48.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.49.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.49.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.49.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.49.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.49.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.49.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.5.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.5.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.5.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.50.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.50.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.50.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.50.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.50.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.50.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.51.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.51.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.51.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.51.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.51.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.51.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.52.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.52.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.52.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.52.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.52.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.52.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.53.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.53.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.53.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.54.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.54.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.54.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.54.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.54.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.54.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.55.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.55.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.55.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.55.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.55.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.55.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.56.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.56.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.56.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.56.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.56.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.56.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.57.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.57.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.57.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.57.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.57.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.57.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.58.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.58.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.58.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.58.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.58.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.58.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.59.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.59.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.59.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.59.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.59.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.59.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.6.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.6.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.6.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.60.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.60.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.60.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.60.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.60.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.60.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.61.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.61.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.61.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.61.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.61.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.61.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.62.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.62.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.62.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.62.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.62.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.62.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.63.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.63.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.63.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.63.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.63.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.63.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.64.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.64.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.64.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.64.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.64.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.64.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.65.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.65.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.65.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.65.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.65.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.65.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.66.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.66.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.66.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.66.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.66.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.66.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.67.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.67.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.67.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.67.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.67.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.67.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.68.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.68.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.68.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.68.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.68.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.68.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.69.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.69.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.69.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.69.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.69.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.69.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.7.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.7.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.7.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.70.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.70.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.70.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.70.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.70.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.70.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.71.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.71.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.71.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.71.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.71.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.71.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.72.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.72.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.72.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.72.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.72.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.72.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.73.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.73.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.73.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.73.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.73.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.73.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.74.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.74.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.74.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.74.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.74.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.74.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.75.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.75.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.75.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.75.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.75.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.75.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.76.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.76.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.76.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.76.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.76.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.76.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.77.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.77.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.77.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.77.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.77.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.77.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.78.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.78.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.78.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.78.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.78.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.78.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.79.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.79.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.79.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.79.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.79.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.79.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.8.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.8.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.8.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.80.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.80.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.80.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.80.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.80.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.80.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.81.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.81.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.81.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.81.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.81.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.81.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.82.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.82.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.82.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.82.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.82.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.82.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.83.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.83.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.83.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.83.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.83.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.83.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.84.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.84.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.84.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.84.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.84.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.84.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.85.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.85.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.85.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.85.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.85.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.85.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.86.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.86.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.86.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.86.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.86.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.86.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.87.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.87.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.87.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.87.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.87.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.87.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.88.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.88.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.88.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.88.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.88.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.88.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.89.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.89.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.89.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.89.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.89.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.89.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.9.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.9.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.9.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.90.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.90.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.90.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.90.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.90.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.90.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.91.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.91.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.91.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.91.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.91.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.91.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.92.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.92.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.92.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.92.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.92.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.92.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.93.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.93.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.93.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.93.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.93.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.93.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.94.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.94.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.94.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.94.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.94.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.94.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.95.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.95.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.95.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.95.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.95.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.95.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.96.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.96.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.96.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.96.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.96.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.96.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.97.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.97.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.97.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.97.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.97.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.97.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.98.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.98.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.98.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.98.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.98.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.98.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.99.w1.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.99.w1.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.99.w2.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.99.w2.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.99.w3.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.experts.99.w3.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.shared_experts.down_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.shared_experts.gate_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.shared_experts.up_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.input_layernorm.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.post_attention_layernorm.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.index_k_norm.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.index_k_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.index_q_norm.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.index_q_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.k_norm.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.k_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.k_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.o_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.o_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.q_norm.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.q_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.q_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.v_proj.weight": "model-00008-of-00059.safetensors", - "language_model.model.layers.8.self_attn.v_proj.weight_scale": "model-00008-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.gate.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.108.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.108.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.108.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.108.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.108.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.108.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.109.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.109.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.109.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.109.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.109.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.109.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.11.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.11.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.11.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.11.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.11.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.11.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.110.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.110.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.110.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.110.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.110.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.110.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.111.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.111.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.111.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.111.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.111.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.111.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.112.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.112.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.112.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.112.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.112.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.112.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.113.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.113.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.113.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.113.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.113.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.113.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.114.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.114.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.114.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.114.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.114.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.114.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.115.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.115.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.115.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.115.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.115.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.115.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.116.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.116.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.116.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.116.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.116.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.116.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.117.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.117.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.117.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.117.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.117.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.117.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.118.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.118.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.118.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.118.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.118.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.118.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.119.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.119.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.119.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.119.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.119.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.119.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.12.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.12.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.12.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.12.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.12.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.12.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.120.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.120.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.120.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.120.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.120.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.120.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.121.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.121.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.121.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.121.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.121.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.121.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.122.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.122.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.122.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.122.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.122.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.122.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.123.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.123.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.123.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.123.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.123.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.123.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.124.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.124.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.124.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.124.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.124.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.124.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.125.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.125.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.125.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.125.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.125.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.125.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.126.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.126.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.126.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.126.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.126.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.126.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.127.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.127.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.127.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.127.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.127.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.127.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.13.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.13.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.13.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.13.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.13.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.13.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.14.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.14.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.14.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.14.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.14.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.14.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.15.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.15.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.15.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.15.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.15.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.15.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.16.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.16.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.16.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.16.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.16.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.16.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.17.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.17.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.17.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.17.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.17.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.17.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.18.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.18.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.18.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.18.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.18.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.18.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.19.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.19.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.19.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.19.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.19.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.19.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.2.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.2.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.2.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.20.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.20.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.20.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.20.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.20.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.20.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.21.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.21.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.21.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.21.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.21.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.21.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.22.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.22.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.22.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.22.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.22.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.22.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.23.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.23.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.23.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.23.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.23.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.23.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.24.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.24.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.24.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.24.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.24.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.24.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.25.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.25.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.25.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.25.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.25.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.25.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.26.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.26.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.26.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.26.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.26.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.26.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.27.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.27.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.27.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.27.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.27.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.27.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.28.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.28.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.28.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.28.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.28.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.28.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.29.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.29.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.29.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.29.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.29.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.29.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.3.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.3.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.3.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.3.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.3.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.3.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.30.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.30.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.30.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.30.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.30.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.30.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.31.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.31.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.31.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.31.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.31.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.31.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.32.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.32.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.32.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.32.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.32.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.32.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.33.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.33.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.33.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.33.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.33.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.33.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.34.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.34.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.34.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.34.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.34.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.34.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.35.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.35.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.35.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.35.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.35.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.35.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.36.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.36.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.36.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.36.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.36.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.36.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.37.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.37.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.37.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.37.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.37.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.37.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.38.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.38.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.38.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.38.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.38.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.38.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.39.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.39.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.39.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.39.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.39.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.39.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.4.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.4.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.4.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.4.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.4.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.4.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.40.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.40.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.40.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.40.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.40.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.40.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.41.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.41.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.41.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.41.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.41.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.41.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.42.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.42.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.42.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.42.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.42.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.42.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.43.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.43.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.43.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.43.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.43.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.43.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.44.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.44.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.44.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.44.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.44.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.44.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.45.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.45.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.45.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.45.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.45.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.45.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.46.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.46.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.46.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.46.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.46.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.46.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.47.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.47.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.47.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.47.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.47.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.47.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.48.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.48.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.48.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.48.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.48.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.48.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.49.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.49.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.49.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.49.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.49.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.49.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.5.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.5.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.5.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.5.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.5.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.5.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.50.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.50.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.50.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.50.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.50.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.50.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.51.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.51.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.51.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.51.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.51.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.51.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.52.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.52.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.52.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.52.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.52.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.52.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.53.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.53.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.53.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.53.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.53.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.53.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.54.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.54.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.54.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.54.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.54.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.54.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.55.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.55.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.55.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.55.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.55.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.55.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.56.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.56.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.56.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.56.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.56.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.56.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.57.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.57.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.57.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.57.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.57.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.57.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.58.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.58.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.58.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.58.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.58.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.58.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.59.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.59.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.59.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.59.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.59.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.59.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.6.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.6.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.6.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.6.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.6.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.6.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.60.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.60.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.60.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.60.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.60.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.60.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.61.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.61.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.61.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.61.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.61.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.61.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.62.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.62.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.62.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.62.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.62.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.62.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.63.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.63.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.63.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.63.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.63.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.63.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.64.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.64.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.64.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.64.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.64.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.64.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.65.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.65.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.65.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.65.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.65.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.65.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.66.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.66.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.66.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.66.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.66.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.66.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.67.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.67.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.67.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.67.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.67.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.67.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.68.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.68.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.68.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.68.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.68.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.68.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.69.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.69.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.69.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.69.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.69.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.69.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.7.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.7.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.7.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.7.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.7.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.7.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.70.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.70.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.70.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.70.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.70.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.70.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.71.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.71.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.71.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.71.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.71.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.71.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.72.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.72.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.72.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.72.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.72.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.72.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.73.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.73.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.73.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.73.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.73.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.73.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.74.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.74.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.74.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.74.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.74.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.74.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.75.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.75.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.75.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.75.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.75.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.75.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.76.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.76.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.76.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.76.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.76.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.76.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.77.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.77.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.77.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.77.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.77.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.77.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.78.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.78.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.78.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.78.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.78.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.78.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.79.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.79.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.79.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.79.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.79.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.79.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.8.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.8.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.8.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.8.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.8.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.8.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.80.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.80.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.80.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.80.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.80.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.80.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.81.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.81.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.81.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.81.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.81.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.81.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.82.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.82.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.82.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.82.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.82.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.82.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.83.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.83.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.83.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.83.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.83.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.83.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.84.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.84.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.84.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.84.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.84.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.84.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.85.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.85.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.85.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.85.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.85.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.85.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.86.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.86.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.86.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.86.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.86.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.86.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.87.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.87.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.87.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.87.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.87.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.87.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.88.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.88.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.88.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.88.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.88.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.88.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.89.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.89.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.89.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.89.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.89.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.89.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.9.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.9.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.9.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.9.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.9.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.9.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.90.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.90.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.90.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.90.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.90.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.90.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.91.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.91.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.91.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.91.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.91.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.91.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.92.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.92.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.92.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.92.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.92.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.92.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.93.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.93.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.93.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.93.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.93.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.93.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.94.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.94.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.94.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.94.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.94.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.94.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.95.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.95.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.95.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.95.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.95.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.95.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.96.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.96.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.96.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.96.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.96.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.96.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.97.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.97.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.97.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.97.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.97.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.97.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.98.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.98.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.98.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.98.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.98.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.98.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.99.w1.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.99.w1.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.99.w2.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.99.w2.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.99.w3.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.99.w3.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.shared_experts.down_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.shared_experts.gate_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.shared_experts.up_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.input_layernorm.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.post_attention_layernorm.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.index_k_norm.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.index_k_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.index_q_norm.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.index_q_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.k_norm.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.k_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.k_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.o_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.o_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.q_norm.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.q_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.q_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.v_proj.weight": "model-00050-of-00059.safetensors", - "language_model.model.layers.50.self_attn.v_proj.weight_scale": "model-00050-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.e_score_correction_bias": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.gate.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.0.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.0.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.0.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.1.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.1.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.1.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.10.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.10.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.10.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.10.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.10.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.10.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.100.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.100.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.100.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.100.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.100.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.100.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.101.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.101.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.101.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.101.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.101.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.101.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.102.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.102.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.102.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.102.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.102.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.102.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.103.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.103.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.103.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.103.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.103.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.103.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.104.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.104.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.104.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.104.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.104.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.104.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.105.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.105.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.105.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.105.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.105.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.105.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.106.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.106.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.106.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.106.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.106.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.106.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.107.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.107.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.107.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.107.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.107.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.107.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.108.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.108.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.108.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.108.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.108.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.108.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.109.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.109.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.109.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.109.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.109.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.109.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.11.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.11.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.11.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.11.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.11.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.11.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.110.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.110.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.110.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.110.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.110.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.110.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.111.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.111.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.111.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.111.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.111.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.111.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.112.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.112.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.112.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.112.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.112.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.112.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.113.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.113.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.113.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.113.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.113.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.113.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.114.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.114.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.114.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.114.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.114.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.114.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.115.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.115.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.115.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.115.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.115.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.115.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.116.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.116.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.116.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.116.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.116.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.116.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.117.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.117.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.117.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.117.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.117.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.117.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.118.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.118.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.118.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.118.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.118.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.118.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.119.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.119.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.119.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.119.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.119.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.119.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.12.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.12.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.12.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.12.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.12.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.12.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.120.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.120.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.120.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.120.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.120.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.120.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.121.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.121.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.121.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.121.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.121.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.121.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.122.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.122.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.122.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.122.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.122.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.122.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.123.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.123.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.123.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.123.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.123.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.123.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.124.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.124.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.124.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.124.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.124.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.124.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.125.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.125.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.125.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.125.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.125.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.125.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.126.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.126.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.126.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.126.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.126.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.126.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.127.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.127.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.127.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.127.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.127.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.127.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.13.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.13.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.13.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.13.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.13.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.13.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.14.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.14.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.14.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.14.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.14.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.14.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.15.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.15.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.15.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.15.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.15.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.15.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.16.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.16.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.16.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.16.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.16.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.16.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.17.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.17.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.17.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.17.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.17.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.17.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.18.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.18.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.18.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.18.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.18.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.18.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.19.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.19.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.19.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.19.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.19.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.19.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.2.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.2.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.2.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.20.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.20.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.20.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.20.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.20.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.20.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.21.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.21.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.21.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.21.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.21.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.21.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.22.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.22.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.22.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.22.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.22.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.22.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.23.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.23.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.23.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.23.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.23.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.23.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.24.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.24.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.24.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.24.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.24.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.24.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.25.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.25.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.25.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.25.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.25.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.25.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.26.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.26.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.26.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.26.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.26.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.26.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.27.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.27.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.27.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.27.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.27.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.27.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.28.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.28.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.28.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.28.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.28.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.28.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.29.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.29.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.29.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.29.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.29.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.29.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.3.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.3.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.3.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.30.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.30.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.30.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.30.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.30.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.30.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.31.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.31.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.31.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.31.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.31.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.31.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.32.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.32.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.32.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.32.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.32.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.32.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.33.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.33.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.33.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.33.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.33.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.33.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.34.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.34.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.34.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.34.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.34.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.34.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.35.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.35.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.35.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.35.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.35.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.35.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.36.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.36.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.36.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.36.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.36.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.36.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.37.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.37.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.37.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.37.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.37.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.37.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.38.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.38.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.38.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.38.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.38.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.38.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.39.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.39.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.39.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.39.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.39.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.39.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.4.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.4.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.4.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.40.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.40.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.40.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.40.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.40.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.40.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.41.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.41.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.41.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.41.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.41.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.41.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.42.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.42.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.42.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.42.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.42.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.42.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.43.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.43.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.43.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.43.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.43.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.43.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.44.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.44.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.44.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.44.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.44.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.44.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.45.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.45.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.45.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.45.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.45.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.45.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.46.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.46.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.46.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.46.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.46.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.46.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.47.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.47.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.47.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.47.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.47.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.47.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.48.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.48.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.48.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.48.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.48.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.48.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.49.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.49.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.49.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.49.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.49.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.49.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.5.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.5.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.5.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.50.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.50.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.50.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.50.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.50.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.50.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.51.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.51.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.51.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.51.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.51.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.51.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.52.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.52.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.52.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.52.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.52.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.52.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.53.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.53.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.53.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.53.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.53.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.53.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.54.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.54.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.54.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.54.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.54.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.54.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.55.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.55.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.55.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.55.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.55.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.55.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.56.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.56.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.56.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.56.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.56.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.56.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.57.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.57.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.57.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.57.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.57.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.57.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.58.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.58.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.58.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.58.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.58.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.58.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.59.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.59.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.59.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.59.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.59.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.59.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.6.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.6.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.6.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.60.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.60.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.60.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.60.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.60.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.60.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.61.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.61.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.61.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.61.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.61.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.61.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.62.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.62.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.62.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.62.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.62.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.62.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.63.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.63.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.63.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.63.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.63.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.63.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.64.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.64.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.64.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.64.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.64.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.64.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.65.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.65.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.65.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.65.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.65.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.65.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.66.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.66.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.66.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.66.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.66.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.66.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.67.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.67.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.67.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.67.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.67.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.67.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.68.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.68.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.68.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.68.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.68.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.68.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.69.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.69.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.69.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.69.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.69.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.69.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.7.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.7.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.7.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.70.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.70.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.70.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.70.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.70.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.70.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.71.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.71.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.71.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.71.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.71.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.71.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.72.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.72.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.72.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.72.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.72.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.72.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.73.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.73.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.73.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.73.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.73.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.73.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.74.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.74.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.74.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.74.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.74.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.74.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.75.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.75.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.75.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.75.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.75.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.75.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.76.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.76.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.76.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.76.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.76.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.76.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.77.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.77.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.77.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.77.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.77.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.77.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.78.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.78.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.78.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.78.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.78.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.78.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.79.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.79.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.79.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.79.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.79.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.79.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.8.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.8.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.8.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.8.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.8.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.8.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.80.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.80.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.80.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.80.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.80.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.80.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.81.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.81.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.81.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.81.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.81.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.81.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.82.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.82.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.82.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.82.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.82.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.82.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.83.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.83.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.83.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.83.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.83.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.83.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.84.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.84.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.84.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.84.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.84.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.84.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.85.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.85.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.85.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.85.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.85.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.85.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.86.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.86.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.86.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.86.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.86.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.86.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.87.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.87.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.87.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.87.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.87.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.87.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.88.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.88.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.88.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.88.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.88.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.88.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.89.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.89.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.89.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.89.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.89.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.89.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.9.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.9.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.9.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.9.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.9.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.9.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.90.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.90.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.90.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.90.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.90.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.90.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.91.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.91.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.91.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.91.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.91.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.91.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.92.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.92.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.92.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.92.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.92.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.92.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.93.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.93.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.93.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.93.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.93.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.93.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.94.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.94.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.94.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.94.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.94.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.94.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.95.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.95.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.95.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.95.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.95.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.95.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.96.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.96.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.96.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.96.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.96.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.96.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.97.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.97.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.97.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.97.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.97.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.97.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.98.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.98.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.98.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.98.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.98.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.98.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.99.w1.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.99.w1.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.99.w2.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.99.w2.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.99.w3.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.experts.99.w3.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.shared_experts.down_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.shared_experts.gate_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.shared_experts.up_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.input_layernorm.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.post_attention_layernorm.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.index_k_norm.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.index_k_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.index_q_norm.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.index_q_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.k_norm.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.k_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.k_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.o_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.o_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.q_norm.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.q_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.q_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.v_proj.weight": "model-00031-of-00059.safetensors", - "language_model.model.layers.31.self_attn.v_proj.weight_scale": "model-00031-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.gate.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.108.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.108.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.108.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.108.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.108.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.108.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.109.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.109.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.109.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.109.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.109.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.109.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.11.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.11.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.11.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.11.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.11.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.11.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.110.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.110.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.110.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.110.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.110.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.110.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.111.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.111.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.111.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.111.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.111.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.111.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.112.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.112.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.112.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.112.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.112.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.112.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.113.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.113.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.113.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.113.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.113.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.113.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.114.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.114.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.114.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.114.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.114.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.114.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.115.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.115.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.115.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.115.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.115.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.115.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.116.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.116.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.116.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.116.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.116.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.116.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.117.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.117.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.117.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.117.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.117.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.117.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.118.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.118.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.118.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.118.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.118.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.118.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.119.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.119.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.119.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.119.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.119.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.119.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.12.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.12.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.12.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.12.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.12.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.12.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.120.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.120.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.120.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.120.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.120.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.120.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.121.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.121.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.121.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.121.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.121.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.121.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.122.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.122.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.122.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.122.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.122.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.122.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.123.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.123.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.123.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.123.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.123.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.123.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.124.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.124.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.124.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.124.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.124.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.124.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.125.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.125.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.125.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.125.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.125.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.125.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.126.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.126.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.126.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.126.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.126.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.126.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.127.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.127.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.127.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.127.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.127.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.127.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.13.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.13.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.13.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.13.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.13.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.13.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.14.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.14.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.14.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.14.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.14.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.14.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.15.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.15.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.15.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.15.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.15.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.15.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.16.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.16.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.16.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.16.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.16.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.16.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.17.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.17.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.17.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.17.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.17.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.17.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.18.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.18.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.18.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.18.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.18.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.18.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.19.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.19.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.19.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.19.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.19.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.19.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.2.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.2.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.2.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.20.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.20.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.20.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.20.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.20.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.20.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.21.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.21.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.21.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.21.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.21.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.21.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.22.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.22.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.22.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.22.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.22.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.22.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.23.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.23.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.23.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.23.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.23.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.23.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.24.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.24.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.24.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.24.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.24.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.24.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.25.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.25.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.25.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.25.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.25.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.25.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.26.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.26.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.26.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.26.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.26.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.26.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.27.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.27.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.27.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.27.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.27.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.27.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.28.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.28.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.28.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.28.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.28.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.28.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.29.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.29.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.29.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.29.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.29.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.29.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.3.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.3.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.3.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.3.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.3.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.3.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.30.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.30.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.30.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.30.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.30.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.30.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.31.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.31.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.31.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.31.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.31.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.31.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.32.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.32.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.32.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.32.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.32.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.32.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.33.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.33.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.33.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.33.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.33.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.33.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.34.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.34.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.34.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.34.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.34.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.34.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.35.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.35.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.35.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.35.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.35.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.35.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.36.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.36.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.36.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.36.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.36.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.36.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.37.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.37.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.37.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.37.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.37.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.37.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.38.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.38.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.38.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.38.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.38.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.38.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.39.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.39.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.39.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.39.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.39.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.39.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.4.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.4.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.4.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.4.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.4.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.4.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.40.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.40.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.40.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.40.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.40.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.40.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.41.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.41.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.41.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.41.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.41.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.41.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.42.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.42.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.42.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.42.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.42.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.42.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.43.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.43.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.43.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.43.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.43.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.43.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.44.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.44.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.44.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.44.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.44.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.44.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.45.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.45.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.45.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.45.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.45.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.45.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.46.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.46.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.46.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.46.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.46.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.46.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.47.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.47.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.47.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.47.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.47.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.47.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.48.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.48.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.48.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.48.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.48.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.48.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.49.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.49.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.49.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.49.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.49.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.49.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.5.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.5.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.5.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.5.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.5.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.5.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.50.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.50.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.50.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.50.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.50.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.50.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.51.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.51.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.51.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.51.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.51.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.51.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.52.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.52.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.52.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.52.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.52.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.52.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.53.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.53.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.53.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.53.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.53.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.53.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.54.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.54.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.54.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.54.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.54.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.54.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.55.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.55.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.55.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.55.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.55.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.55.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.56.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.56.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.56.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.56.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.56.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.56.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.57.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.57.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.57.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.57.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.57.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.57.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.58.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.58.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.58.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.58.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.58.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.58.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.59.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.59.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.59.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.59.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.59.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.59.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.6.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.6.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.6.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.6.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.6.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.6.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.60.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.60.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.60.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.60.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.60.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.60.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.61.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.61.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.61.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.61.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.61.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.61.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.62.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.62.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.62.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.62.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.62.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.62.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.63.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.63.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.63.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.63.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.63.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.63.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.64.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.64.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.64.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.64.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.64.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.64.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.65.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.65.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.65.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.65.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.65.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.65.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.66.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.66.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.66.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.66.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.66.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.66.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.67.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.67.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.67.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.67.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.67.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.67.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.68.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.68.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.68.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.68.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.68.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.68.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.69.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.69.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.69.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.69.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.69.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.69.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.7.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.7.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.7.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.7.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.7.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.7.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.70.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.70.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.70.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.70.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.70.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.70.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.71.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.71.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.71.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.71.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.71.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.71.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.72.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.72.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.72.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.72.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.72.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.72.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.73.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.73.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.73.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.73.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.73.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.73.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.74.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.74.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.74.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.74.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.74.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.74.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.75.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.75.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.75.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.75.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.75.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.75.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.76.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.76.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.76.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.76.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.76.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.76.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.77.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.77.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.77.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.77.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.77.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.77.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.78.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.78.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.78.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.78.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.78.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.78.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.79.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.79.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.79.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.79.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.79.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.79.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.8.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.8.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.8.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.8.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.8.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.8.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.80.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.80.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.80.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.80.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.80.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.80.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.81.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.81.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.81.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.81.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.81.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.81.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.82.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.82.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.82.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.82.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.82.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.82.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.83.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.83.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.83.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.83.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.83.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.83.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.84.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.84.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.84.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.84.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.84.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.84.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.85.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.85.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.85.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.85.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.85.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.85.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.86.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.86.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.86.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.86.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.86.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.86.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.87.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.87.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.87.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.87.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.87.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.87.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.88.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.88.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.88.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.88.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.88.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.88.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.89.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.89.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.89.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.89.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.89.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.89.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.9.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.9.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.9.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.9.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.9.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.9.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.90.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.90.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.90.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.90.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.90.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.90.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.91.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.91.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.91.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.91.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.91.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.91.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.92.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.92.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.92.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.92.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.92.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.92.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.93.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.93.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.93.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.93.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.93.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.93.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.94.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.94.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.94.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.94.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.94.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.94.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.95.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.95.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.95.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.95.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.95.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.95.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.96.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.96.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.96.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.96.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.96.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.96.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.97.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.97.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.97.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.97.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.97.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.97.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.98.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.98.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.98.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.98.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.98.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.98.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.99.w1.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.99.w1.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.99.w2.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.99.w2.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.99.w3.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.99.w3.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.shared_experts.down_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.shared_experts.gate_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.shared_experts.up_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.input_layernorm.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.post_attention_layernorm.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.index_k_norm.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.index_k_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.index_q_norm.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.index_q_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.k_norm.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.k_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.k_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.o_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.o_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.q_norm.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.q_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.q_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.v_proj.weight": "model-00055-of-00059.safetensors", - "language_model.model.layers.55.self_attn.v_proj.weight_scale": "model-00055-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.e_score_correction_bias": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.e_score_correction_bias": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.0.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.0.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.0.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.1.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.1.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.1.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.10.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.10.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.10.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.100.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.100.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.100.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.101.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.101.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.101.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.102.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.102.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.102.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.103.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.103.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.103.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.104.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.104.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.104.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.105.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.105.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.105.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.106.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.106.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.106.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.107.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.107.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.107.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.0.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.0.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.0.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.1.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.1.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.1.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.10.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.10.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.10.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.100.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.100.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.100.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.101.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.101.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.101.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.102.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.102.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.102.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.103.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.103.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.103.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.104.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.104.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.104.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.105.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.105.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.105.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.106.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.106.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.106.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.107.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.107.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.107.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.108.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.108.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.108.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.109.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.109.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.109.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.11.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.11.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.11.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.110.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.110.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.110.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.111.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.111.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.111.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.112.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.112.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.112.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.113.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.113.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.113.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.114.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.114.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.114.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.114.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.114.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.115.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.115.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.115.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.115.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.115.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.115.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.116.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.116.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.116.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.116.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.116.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.116.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.117.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.117.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.117.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.117.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.117.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.117.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.118.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.118.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.118.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.118.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.118.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.118.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.119.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.119.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.119.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.119.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.119.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.119.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.12.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.12.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.12.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.120.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.120.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.120.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.120.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.120.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.120.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.121.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.121.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.121.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.121.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.121.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.121.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.122.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.122.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.122.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.122.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.122.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.122.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.123.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.123.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.123.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.123.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.123.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.123.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.124.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.124.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.124.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.124.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.124.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.124.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.125.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.125.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.125.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.125.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.125.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.125.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.126.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.126.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.126.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.126.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.126.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.126.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.127.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.127.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.127.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.127.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.127.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.127.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.13.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.13.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.13.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.14.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.14.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.14.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.15.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.15.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.15.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.16.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.16.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.16.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.17.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.17.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.17.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.18.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.18.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.18.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.19.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.19.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.19.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.2.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.2.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.2.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.20.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.20.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.20.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.21.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.21.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.21.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.22.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.22.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.22.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.23.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.23.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.23.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.24.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.24.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.24.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.25.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.25.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.25.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.26.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.26.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.26.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.27.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.27.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.27.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.28.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.28.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.28.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.29.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.29.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.29.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.3.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.3.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.3.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.30.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.30.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.30.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.31.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.31.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.31.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.32.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.32.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.32.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.33.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.33.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.33.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.34.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.34.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.34.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.35.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.35.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.35.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.36.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.36.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.36.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.37.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.37.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.37.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.38.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.38.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.38.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.39.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.39.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.39.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.4.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.4.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.4.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.40.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.40.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.40.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.41.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.41.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.41.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.41.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.42.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.42.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.42.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.43.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.43.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.43.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.44.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.44.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.44.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.45.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.45.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.45.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.46.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.46.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.46.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.47.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.47.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.47.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.48.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.48.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.48.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.49.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.49.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.49.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.5.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.5.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.5.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.50.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.50.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.50.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.51.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.51.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.51.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.52.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.52.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.52.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.53.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.53.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.53.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.54.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.54.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.54.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.55.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.55.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.55.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.56.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.56.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.56.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.57.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.57.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.57.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.58.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.58.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.58.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.59.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.59.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.59.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.6.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.6.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.6.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.60.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.60.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.60.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.61.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.61.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.61.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.62.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.62.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.62.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.63.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.63.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.63.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.64.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.64.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.64.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.64.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.64.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.64.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.65.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.65.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.65.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.65.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.65.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.65.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.66.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.66.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.66.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.66.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.66.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.66.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.67.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.67.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.67.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.67.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.67.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.67.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.68.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.68.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.68.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.68.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.68.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.68.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.69.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.69.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.69.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.69.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.69.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.69.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.7.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.7.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.7.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.70.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.70.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.70.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.70.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.70.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.70.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.71.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.71.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.71.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.71.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.71.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.71.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.72.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.72.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.72.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.72.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.72.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.72.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.73.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.73.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.73.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.73.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.73.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.73.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.74.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.74.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.74.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.74.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.74.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.74.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.75.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.75.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.75.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.75.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.75.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.75.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.76.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.76.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.76.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.76.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.76.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.76.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.77.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.77.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.77.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.77.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.77.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.77.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.78.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.78.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.78.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.78.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.78.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.78.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.79.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.79.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.79.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.79.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.79.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.79.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.8.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.8.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.8.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.80.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.80.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.80.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.80.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.80.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.80.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.81.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.81.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.81.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.81.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.81.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.81.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.82.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.82.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.82.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.82.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.82.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.82.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.83.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.83.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.83.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.83.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.83.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.83.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.84.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.84.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.84.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.84.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.84.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.84.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.85.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.85.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.85.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.85.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.85.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.85.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.86.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.86.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.86.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.86.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.86.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.86.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.87.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.87.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.87.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.87.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.87.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.87.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.88.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.88.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.88.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.88.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.88.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.88.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.89.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.89.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.89.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.89.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.89.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.89.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.9.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.9.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.9.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.90.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.90.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.90.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.90.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.90.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.90.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.91.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.91.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.91.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.91.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.91.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.91.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.92.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.92.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.92.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.92.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.92.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.92.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.93.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.93.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.93.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.93.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.93.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.93.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.94.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.94.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.94.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.94.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.94.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.94.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.95.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.95.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.95.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.95.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.95.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.95.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.96.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.96.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.96.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.96.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.96.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.96.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.97.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.97.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.97.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.97.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.97.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.97.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.98.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.98.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.98.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.98.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.98.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.98.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.99.w1.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.99.w1.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.99.w2.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.99.w2.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.99.w3.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.experts.99.w3.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.shared_experts.down_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.shared_experts.gate_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.shared_experts.up_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.input_layernorm.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.post_attention_layernorm.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.index_k_norm.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.index_k_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.index_q_norm.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.index_q_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.k_norm.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.k_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.k_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.o_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.o_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.q_norm.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.q_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.q_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.v_proj.weight": "model-00005-of-00059.safetensors", - "language_model.model.layers.5.self_attn.v_proj.weight_scale": "model-00005-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.e_score_correction_bias": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.gate.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.0.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.0.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.0.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.1.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.1.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.1.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.10.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.10.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.10.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.10.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.10.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.10.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.100.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.100.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.100.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.100.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.100.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.100.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.101.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.101.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.101.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.101.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.101.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.101.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.102.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.102.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.102.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.102.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.102.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.102.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.103.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.103.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.103.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.103.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.103.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.103.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.104.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.104.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.104.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.104.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.104.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.104.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.105.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.105.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.105.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.105.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.105.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.105.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.106.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.106.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.106.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.106.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.106.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.106.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.107.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.107.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.107.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.107.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.107.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.107.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.108.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.108.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.108.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.108.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.108.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.108.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.109.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.109.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.109.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.109.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.109.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.109.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.11.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.11.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.11.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.11.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.11.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.11.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.110.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.110.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.110.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.110.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.110.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.110.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.111.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.111.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.111.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.111.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.111.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.111.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.112.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.112.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.112.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.112.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.112.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.112.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.113.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.113.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.113.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.113.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.113.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.113.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.114.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.114.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.114.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.114.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.114.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.114.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.115.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.115.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.115.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.115.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.115.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.115.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.116.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.116.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.116.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.116.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.116.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.116.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.117.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.117.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.117.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.117.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.117.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.117.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.118.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.118.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.118.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.118.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.118.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.118.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.119.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.119.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.119.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.119.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.119.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.119.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.12.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.12.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.12.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.12.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.12.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.12.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.120.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.120.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.120.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.120.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.120.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.120.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.121.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.121.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.121.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.121.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.121.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.121.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.122.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.122.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.122.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.122.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.122.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.122.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.123.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.123.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.123.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.123.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.123.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.123.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.124.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.124.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.124.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.124.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.124.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.124.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.125.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.125.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.125.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.125.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.125.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.125.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.126.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.126.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.126.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.126.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.126.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.126.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.127.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.127.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.127.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.127.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.127.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.127.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.13.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.13.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.13.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.13.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.13.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.13.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.14.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.14.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.14.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.14.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.14.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.14.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.15.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.15.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.15.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.15.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.15.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.15.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.16.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.16.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.16.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.16.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.16.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.16.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.17.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.17.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.17.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.17.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.17.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.17.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.18.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.18.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.18.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.18.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.18.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.18.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.19.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.19.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.19.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.19.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.19.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.19.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.2.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.2.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.2.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.20.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.20.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.20.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.20.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.20.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.20.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.21.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.21.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.21.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.21.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.21.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.21.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.22.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.22.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.22.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.22.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.22.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.22.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.23.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.23.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.23.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.23.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.23.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.23.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.24.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.24.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.24.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.24.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.24.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.24.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.25.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.25.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.25.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.25.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.25.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.25.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.26.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.26.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.26.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.26.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.26.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.26.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.27.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.27.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.27.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.27.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.27.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.27.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.28.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.28.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.28.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.28.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.28.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.28.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.29.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.29.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.29.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.29.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.29.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.29.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.3.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.3.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.3.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.30.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.30.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.30.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.30.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.30.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.30.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.31.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.31.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.31.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.31.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.31.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.31.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.32.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.32.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.32.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.32.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.32.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.32.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.33.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.33.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.33.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.33.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.33.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.33.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.34.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.34.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.34.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.34.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.34.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.34.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.35.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.35.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.35.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.35.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.35.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.35.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.36.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.36.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.36.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.36.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.36.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.36.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.37.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.37.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.37.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.37.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.37.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.37.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.38.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.38.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.38.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.38.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.38.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.38.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.39.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.39.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.39.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.39.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.39.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.39.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.4.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.4.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.4.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.40.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.40.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.40.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.40.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.40.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.40.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.41.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.41.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.41.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.41.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.41.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.41.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.42.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.42.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.42.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.42.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.42.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.42.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.43.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.43.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.43.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.43.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.43.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.43.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.44.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.44.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.44.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.44.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.44.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.44.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.45.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.45.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.45.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.45.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.45.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.45.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.46.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.46.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.46.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.46.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.46.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.46.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.47.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.47.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.47.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.47.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.47.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.47.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.48.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.48.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.48.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.48.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.48.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.48.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.49.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.49.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.49.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.49.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.49.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.49.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.5.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.5.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.5.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.50.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.50.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.50.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.50.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.50.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.50.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.51.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.51.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.51.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.51.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.51.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.51.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.52.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.52.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.52.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.52.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.52.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.52.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.53.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.53.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.53.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.53.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.53.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.53.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.54.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.54.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.54.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.54.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.54.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.54.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.55.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.55.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.55.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.55.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.55.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.55.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.56.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.56.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.56.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.56.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.56.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.56.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.57.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.57.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.57.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.57.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.57.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.57.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.58.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.58.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.58.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.58.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.58.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.58.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.59.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.59.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.59.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.59.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.59.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.59.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.6.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.6.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.6.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.60.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.60.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.60.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.60.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.60.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.60.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.61.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.61.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.61.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.61.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.61.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.61.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.62.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.62.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.62.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.62.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.62.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.62.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.63.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.63.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.63.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.63.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.63.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.63.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.64.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.64.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.64.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.64.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.64.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.64.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.65.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.65.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.65.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.65.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.65.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.65.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.66.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.66.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.66.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.66.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.66.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.66.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.67.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.67.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.67.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.67.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.67.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.67.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.68.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.68.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.68.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.68.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.68.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.68.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.69.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.69.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.69.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.69.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.69.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.69.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.7.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.7.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.7.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.70.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.70.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.70.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.70.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.70.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.70.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.71.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.71.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.71.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.71.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.71.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.71.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.72.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.72.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.72.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.72.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.72.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.72.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.73.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.73.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.73.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.73.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.73.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.73.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.74.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.74.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.74.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.74.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.74.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.74.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.75.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.75.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.75.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.75.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.75.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.75.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.76.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.76.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.76.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.76.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.76.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.76.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.77.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.77.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.77.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.77.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.77.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.77.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.78.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.78.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.78.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.78.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.78.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.78.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.79.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.79.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.79.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.79.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.79.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.79.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.8.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.8.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.8.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.8.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.8.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.8.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.80.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.80.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.80.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.80.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.80.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.80.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.81.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.81.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.81.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.81.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.81.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.81.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.82.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.82.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.82.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.82.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.82.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.82.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.83.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.83.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.83.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.83.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.83.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.83.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.84.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.84.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.84.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.84.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.84.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.84.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.85.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.85.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.85.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.85.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.85.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.85.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.86.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.86.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.86.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.86.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.86.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.86.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.87.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.87.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.87.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.87.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.87.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.87.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.88.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.88.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.88.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.88.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.88.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.88.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.89.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.89.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.89.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.89.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.89.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.89.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.9.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.9.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.9.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.9.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.9.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.9.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.90.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.90.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.90.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.90.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.90.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.90.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.91.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.91.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.91.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.91.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.91.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.91.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.92.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.92.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.92.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.92.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.92.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.92.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.93.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.93.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.93.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.93.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.93.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.93.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.94.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.94.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.94.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.94.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.94.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.94.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.95.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.95.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.95.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.95.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.95.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.95.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.96.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.96.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.96.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.96.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.96.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.96.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.97.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.97.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.97.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.97.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.97.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.97.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.98.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.98.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.98.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.98.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.98.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.98.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.99.w1.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.99.w1.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.99.w2.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.99.w2.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.99.w3.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.experts.99.w3.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.shared_experts.down_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.shared_experts.gate_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.shared_experts.up_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.input_layernorm.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.post_attention_layernorm.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.index_k_norm.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.index_k_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.index_q_norm.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.index_q_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.k_norm.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.k_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.k_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.o_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.o_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.q_norm.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.q_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.q_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.v_proj.weight": "model-00036-of-00059.safetensors", - "language_model.model.layers.36.self_attn.v_proj.weight_scale": "model-00036-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.e_score_correction_bias": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.gate.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.e_score_correction_bias": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.0.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.0.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.0.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.1.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.1.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.1.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.10.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.10.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.10.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.100.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.100.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.100.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.101.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.101.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.101.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.102.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.102.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.102.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.103.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.103.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.103.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.104.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.104.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.104.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.105.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.105.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.105.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.106.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.106.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.106.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.107.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.107.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.107.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.108.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.108.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.108.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.108.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.108.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.108.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.109.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.109.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.109.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.109.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.109.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.109.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.11.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.11.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.11.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.110.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.110.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.110.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.110.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.110.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.110.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.111.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.111.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.111.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.111.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.111.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.111.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.112.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.112.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.112.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.112.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.112.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.112.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.113.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.113.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.113.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.113.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.113.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.113.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.114.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.114.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.114.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.114.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.114.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.114.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.115.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.115.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.115.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.115.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.115.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.115.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.116.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.116.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.116.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.116.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.116.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.116.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.117.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.117.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.117.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.117.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.117.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.117.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.118.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.118.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.118.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.118.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.118.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.118.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.119.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.119.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.119.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.119.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.119.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.119.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.12.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.12.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.12.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.120.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.120.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.120.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.120.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.120.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.120.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.121.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.121.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.121.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.121.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.121.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.121.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.122.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.122.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.122.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.122.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.122.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.122.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.123.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.123.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.123.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.123.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.123.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.123.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.124.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.124.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.124.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.124.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.124.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.124.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.125.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.125.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.125.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.125.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.125.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.125.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.126.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.126.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.126.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.126.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.126.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.126.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.127.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.127.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.127.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.127.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.127.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.127.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.13.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.13.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.13.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.14.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.14.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.14.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.15.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.15.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.15.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.15.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.15.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.16.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.16.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.16.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.16.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.16.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.16.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.17.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.17.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.17.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.17.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.17.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.17.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.18.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.18.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.18.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.18.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.18.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.18.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.19.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.19.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.19.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.19.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.19.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.19.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.2.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.2.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.2.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.20.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.20.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.20.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.20.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.20.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.20.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.21.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.21.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.21.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.21.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.21.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.21.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.22.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.22.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.22.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.22.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.22.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.22.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.23.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.23.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.23.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.23.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.23.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.23.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.24.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.24.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.24.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.24.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.24.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.24.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.25.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.25.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.25.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.25.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.25.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.25.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.26.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.26.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.26.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.26.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.26.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.26.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.27.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.27.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.27.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.27.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.27.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.27.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.28.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.28.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.28.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.28.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.28.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.28.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.29.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.29.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.29.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.29.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.29.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.29.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.3.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.3.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.3.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.30.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.30.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.30.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.30.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.30.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.30.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.31.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.31.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.31.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.31.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.31.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.31.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.32.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.32.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.32.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.32.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.32.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.32.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.33.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.33.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.33.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.33.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.33.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.33.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.34.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.34.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.34.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.34.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.34.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.34.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.35.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.35.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.35.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.35.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.35.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.35.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.36.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.36.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.36.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.36.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.36.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.36.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.37.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.37.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.37.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.37.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.37.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.37.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.38.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.38.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.38.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.38.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.38.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.38.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.39.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.39.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.39.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.39.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.39.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.39.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.4.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.4.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.4.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.40.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.40.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.40.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.40.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.40.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.40.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.41.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.41.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.41.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.41.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.41.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.41.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.42.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.42.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.42.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.42.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.42.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.42.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.43.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.43.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.43.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.43.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.43.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.43.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.44.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.44.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.44.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.44.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.44.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.44.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.45.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.45.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.45.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.45.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.45.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.45.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.46.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.46.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.46.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.46.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.46.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.46.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.47.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.47.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.47.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.47.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.47.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.47.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.48.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.48.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.48.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.48.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.48.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.48.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.49.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.49.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.49.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.49.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.49.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.49.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.5.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.5.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.5.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.50.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.50.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.50.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.50.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.50.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.50.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.51.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.51.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.51.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.51.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.51.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.51.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.52.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.52.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.52.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.52.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.52.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.52.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.53.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.53.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.53.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.53.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.53.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.53.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.54.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.54.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.54.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.54.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.54.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.54.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.55.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.55.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.55.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.55.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.55.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.55.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.56.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.56.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.56.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.56.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.56.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.56.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.57.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.57.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.57.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.57.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.57.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.57.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.58.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.58.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.58.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.58.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.58.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.58.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.59.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.59.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.59.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.59.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.59.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.59.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.6.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.6.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.6.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.60.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.60.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.60.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.60.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.60.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.60.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.61.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.61.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.61.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.61.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.61.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.61.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.62.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.62.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.62.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.62.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.62.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.62.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.63.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.63.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.63.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.63.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.63.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.63.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.64.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.64.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.64.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.64.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.64.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.64.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.65.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.65.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.65.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.65.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.65.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.65.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.66.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.66.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.66.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.66.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.66.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.66.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.67.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.67.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.67.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.67.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.67.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.67.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.68.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.68.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.68.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.68.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.68.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.68.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.69.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.69.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.69.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.69.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.69.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.69.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.7.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.7.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.7.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.70.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.70.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.70.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.70.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.70.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.70.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.71.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.71.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.71.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.71.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.71.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.71.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.72.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.72.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.72.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.72.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.72.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.72.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.73.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.73.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.73.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.73.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.73.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.73.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.74.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.74.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.74.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.74.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.74.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.74.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.75.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.75.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.75.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.75.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.75.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.75.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.76.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.76.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.76.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.76.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.76.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.76.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.77.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.77.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.77.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.77.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.77.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.77.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.78.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.78.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.78.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.78.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.78.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.78.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.79.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.79.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.79.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.79.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.79.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.79.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.8.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.8.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.8.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.8.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.8.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.8.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.80.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.80.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.80.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.80.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.80.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.80.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.81.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.81.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.81.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.81.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.81.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.81.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.82.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.82.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.82.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.82.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.82.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.82.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.83.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.83.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.83.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.83.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.83.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.83.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.84.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.84.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.84.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.84.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.84.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.84.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.85.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.85.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.85.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.85.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.85.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.85.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.86.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.86.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.86.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.86.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.86.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.86.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.87.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.87.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.87.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.87.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.87.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.87.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.88.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.88.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.88.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.88.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.88.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.88.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.89.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.89.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.89.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.89.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.89.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.89.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.9.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.9.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.9.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.9.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.9.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.9.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.90.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.90.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.90.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.90.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.90.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.90.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.91.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.91.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.91.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.91.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.91.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.91.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.92.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.92.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.92.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.92.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.92.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.92.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.93.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.93.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.93.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.93.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.93.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.93.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.94.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.94.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.94.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.94.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.94.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.94.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.95.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.95.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.95.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.95.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.95.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.95.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.96.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.96.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.96.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.96.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.96.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.96.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.97.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.97.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.97.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.97.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.97.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.97.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.98.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.98.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.98.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.98.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.98.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.98.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.99.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.99.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.99.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.99.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.99.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.experts.99.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.shared_experts.down_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.shared_experts.gate_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.shared_experts.up_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.input_layernorm.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.post_attention_layernorm.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.index_k_norm.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.index_k_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.index_q_norm.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.index_q_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.k_norm.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.k_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.k_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.o_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.o_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.q_norm.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.q_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.q_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.v_proj.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.17.self_attn.v_proj.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.0.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.0.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.0.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.1.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.1.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.1.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.10.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.10.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.10.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.100.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.100.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.100.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.101.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.101.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.101.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.102.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.102.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.102.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.103.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.103.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.103.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.104.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.104.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.104.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.105.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.105.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.105.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.106.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.106.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.106.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.107.w1.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.107.w2.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.107.w3.weight_scale": "model-00017-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.gate.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.108.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.108.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.108.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.108.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.108.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.108.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.109.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.109.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.109.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.109.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.109.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.109.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.11.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.11.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.11.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.11.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.11.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.11.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.110.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.110.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.110.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.110.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.110.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.110.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.111.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.111.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.111.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.111.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.111.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.111.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.112.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.112.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.112.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.112.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.112.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.112.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.113.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.113.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.113.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.113.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.113.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.113.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.114.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.114.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.114.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.114.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.114.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.114.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.115.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.115.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.115.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.115.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.115.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.115.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.116.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.116.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.116.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.116.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.116.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.116.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.117.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.117.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.117.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.117.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.117.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.117.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.118.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.118.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.118.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.118.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.118.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.118.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.119.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.119.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.119.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.119.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.119.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.119.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.12.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.12.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.12.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.12.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.12.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.12.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.120.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.120.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.120.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.120.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.120.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.120.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.121.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.121.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.121.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.121.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.121.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.121.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.122.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.122.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.122.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.122.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.122.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.122.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.123.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.123.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.123.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.123.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.123.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.123.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.124.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.124.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.124.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.124.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.124.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.124.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.125.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.125.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.125.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.125.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.125.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.125.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.126.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.126.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.126.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.126.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.126.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.126.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.127.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.127.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.127.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.127.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.127.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.127.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.13.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.13.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.13.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.13.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.13.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.13.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.14.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.14.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.14.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.14.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.14.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.14.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.15.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.15.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.15.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.15.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.15.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.15.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.16.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.16.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.16.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.16.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.16.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.16.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.17.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.17.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.17.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.17.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.17.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.17.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.18.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.18.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.18.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.18.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.18.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.18.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.19.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.19.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.19.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.19.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.19.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.19.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.2.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.2.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.2.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.2.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.2.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.2.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.20.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.20.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.20.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.20.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.20.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.20.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.21.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.21.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.21.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.21.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.21.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.21.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.22.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.22.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.22.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.22.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.22.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.22.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.23.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.23.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.23.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.23.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.23.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.23.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.24.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.24.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.24.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.24.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.24.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.24.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.25.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.25.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.25.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.25.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.25.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.25.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.26.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.26.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.26.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.26.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.26.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.26.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.27.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.27.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.27.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.27.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.27.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.27.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.28.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.28.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.28.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.28.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.28.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.28.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.29.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.29.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.29.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.29.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.29.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.29.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.3.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.3.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.3.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.3.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.3.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.3.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.30.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.30.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.30.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.30.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.30.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.30.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.31.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.31.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.31.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.31.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.31.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.31.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.32.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.32.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.32.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.32.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.32.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.32.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.33.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.33.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.33.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.33.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.33.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.33.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.34.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.34.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.34.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.34.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.34.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.34.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.35.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.35.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.35.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.35.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.35.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.35.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.36.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.36.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.36.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.36.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.36.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.36.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.37.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.37.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.37.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.37.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.37.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.37.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.38.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.38.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.38.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.38.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.38.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.38.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.39.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.39.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.39.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.39.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.39.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.39.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.4.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.4.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.4.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.4.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.4.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.4.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.40.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.40.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.40.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.40.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.40.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.40.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.41.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.41.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.41.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.41.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.41.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.41.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.42.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.42.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.42.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.42.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.42.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.42.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.43.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.43.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.43.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.43.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.43.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.43.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.44.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.44.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.44.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.44.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.44.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.44.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.45.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.45.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.45.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.45.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.45.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.45.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.46.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.46.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.46.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.46.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.46.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.46.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.47.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.47.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.47.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.47.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.47.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.47.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.48.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.48.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.48.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.48.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.48.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.48.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.49.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.49.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.49.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.49.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.49.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.49.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.5.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.5.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.5.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.5.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.5.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.5.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.50.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.50.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.50.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.50.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.50.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.50.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.51.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.51.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.51.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.51.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.51.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.51.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.52.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.52.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.52.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.52.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.52.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.52.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.53.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.53.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.53.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.53.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.53.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.53.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.54.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.54.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.54.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.54.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.54.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.54.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.55.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.55.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.55.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.55.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.55.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.55.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.56.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.56.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.56.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.56.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.56.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.56.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.57.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.57.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.57.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.57.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.57.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.57.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.58.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.58.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.58.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.58.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.58.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.58.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.59.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.59.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.59.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.59.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.59.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.59.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.6.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.6.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.6.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.6.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.6.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.6.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.60.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.60.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.60.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.60.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.60.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.60.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.61.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.61.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.61.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.61.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.61.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.61.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.62.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.62.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.62.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.62.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.62.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.62.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.63.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.63.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.63.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.63.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.63.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.63.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.64.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.64.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.64.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.64.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.64.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.64.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.65.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.65.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.65.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.65.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.65.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.65.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.66.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.66.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.66.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.66.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.66.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.66.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.67.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.67.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.67.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.67.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.67.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.67.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.68.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.68.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.68.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.68.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.68.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.68.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.69.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.69.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.69.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.69.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.69.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.69.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.7.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.7.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.7.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.7.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.7.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.7.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.70.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.70.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.70.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.70.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.70.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.70.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.71.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.71.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.71.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.71.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.71.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.71.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.72.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.72.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.72.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.72.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.72.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.72.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.73.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.73.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.73.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.73.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.73.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.73.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.74.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.74.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.74.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.74.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.74.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.74.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.75.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.75.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.75.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.75.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.75.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.75.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.76.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.76.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.76.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.76.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.76.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.76.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.77.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.77.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.77.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.77.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.77.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.77.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.78.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.78.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.78.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.78.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.78.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.78.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.79.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.79.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.79.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.79.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.79.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.79.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.8.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.8.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.8.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.8.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.8.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.8.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.80.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.80.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.80.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.80.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.80.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.80.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.81.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.81.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.81.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.81.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.81.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.81.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.82.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.82.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.82.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.82.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.82.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.82.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.83.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.83.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.83.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.83.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.83.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.83.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.84.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.84.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.84.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.84.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.84.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.84.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.85.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.85.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.85.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.85.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.85.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.85.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.86.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.86.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.86.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.86.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.86.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.86.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.87.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.87.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.87.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.87.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.87.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.87.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.88.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.88.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.88.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.88.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.88.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.88.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.89.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.89.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.89.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.89.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.89.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.89.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.9.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.9.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.9.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.9.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.9.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.9.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.90.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.90.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.90.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.90.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.90.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.90.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.91.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.91.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.91.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.91.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.91.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.91.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.92.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.92.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.92.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.92.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.92.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.92.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.93.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.93.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.93.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.93.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.93.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.93.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.94.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.94.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.94.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.94.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.94.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.94.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.95.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.95.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.95.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.95.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.95.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.95.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.96.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.96.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.96.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.96.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.96.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.96.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.97.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.97.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.97.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.97.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.97.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.97.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.98.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.98.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.98.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.98.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.98.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.98.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.99.w1.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.99.w1.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.99.w2.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.99.w2.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.99.w3.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.99.w3.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.shared_experts.down_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.shared_experts.gate_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.shared_experts.up_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.input_layernorm.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.post_attention_layernorm.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.index_k_norm.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.index_k_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.index_q_norm.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.index_q_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.k_norm.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.k_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.k_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.o_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.o_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.q_norm.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.q_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.q_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.v_proj.weight": "model-00057-of-00059.safetensors", - "language_model.model.layers.57.self_attn.v_proj.weight_scale": "model-00057-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.e_score_correction_bias": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.e_score_correction_bias": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.0.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.0.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.0.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.1.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.1.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.1.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.10.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.10.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.10.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.100.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.100.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.100.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.101.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.101.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.101.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.102.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.102.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.102.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.103.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.103.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.103.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.104.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.104.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.104.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.105.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.105.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.105.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.106.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.106.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.106.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.107.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.107.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.40.block_sparse_moe.experts.107.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.0.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.0.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.0.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.1.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.1.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.1.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.10.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.10.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.10.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.100.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.100.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.100.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.101.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.101.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.101.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.102.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.102.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.102.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.103.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.103.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.103.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.104.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.104.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.104.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.105.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.105.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.105.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.106.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.106.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.106.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.107.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.107.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.107.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.108.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.108.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.108.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.108.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.108.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.108.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.109.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.109.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.109.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.109.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.109.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.109.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.11.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.11.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.11.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.110.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.110.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.110.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.110.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.110.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.110.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.111.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.111.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.111.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.111.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.111.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.111.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.112.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.112.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.112.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.112.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.112.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.112.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.113.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.113.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.113.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.113.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.113.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.113.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.114.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.114.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.114.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.114.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.114.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.114.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.115.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.115.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.115.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.115.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.115.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.115.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.116.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.116.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.116.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.116.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.116.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.116.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.117.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.117.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.117.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.117.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.117.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.117.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.118.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.118.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.118.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.118.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.118.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.118.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.119.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.119.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.119.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.119.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.119.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.119.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.12.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.12.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.12.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.120.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.120.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.120.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.120.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.120.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.120.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.121.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.121.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.121.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.121.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.121.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.121.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.122.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.122.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.122.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.122.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.122.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.122.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.123.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.123.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.123.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.123.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.123.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.123.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.124.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.124.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.124.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.124.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.124.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.124.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.125.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.125.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.125.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.125.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.125.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.125.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.126.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.126.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.126.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.126.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.126.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.126.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.127.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.127.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.127.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.127.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.127.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.127.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.13.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.13.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.13.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.14.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.14.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.14.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.15.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.15.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.15.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.16.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.16.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.16.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.17.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.17.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.17.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.18.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.18.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.18.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.19.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.19.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.19.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.2.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.2.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.2.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.20.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.20.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.20.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.21.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.21.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.21.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.22.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.22.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.22.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.23.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.23.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.23.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.24.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.24.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.24.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.25.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.25.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.25.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.26.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.26.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.26.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.27.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.27.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.27.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.28.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.28.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.28.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.29.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.29.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.29.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.3.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.3.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.3.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.30.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.30.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.30.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.31.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.31.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.31.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.32.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.32.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.32.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.33.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.33.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.33.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.34.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.34.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.34.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.35.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.35.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.35.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.36.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.36.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.36.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.37.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.37.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.37.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.38.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.38.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.38.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.39.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.39.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.39.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.4.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.4.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.4.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.40.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.40.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.40.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.41.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.41.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.41.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.42.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.42.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.42.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.43.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.43.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.43.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.44.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.44.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.44.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.45.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.45.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.45.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.46.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.46.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.46.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.47.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.47.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.47.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.48.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.48.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.48.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.49.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.49.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.49.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.49.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.5.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.5.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.5.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.50.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.50.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.50.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.51.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.51.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.51.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.52.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.52.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.52.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.53.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.53.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.53.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.54.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.54.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.54.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.55.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.55.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.55.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.56.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.56.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.56.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.57.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.57.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.57.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.58.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.58.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.58.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.59.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.59.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.59.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.6.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.6.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.6.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.60.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.60.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.60.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.61.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.61.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.61.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.62.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.62.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.62.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.63.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.63.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.63.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.64.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.64.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.64.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.64.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.64.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.64.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.65.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.65.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.65.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.65.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.65.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.65.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.66.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.66.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.66.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.66.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.66.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.66.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.67.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.67.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.67.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.67.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.67.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.67.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.68.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.68.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.68.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.68.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.68.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.68.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.69.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.69.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.69.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.69.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.69.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.69.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.7.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.7.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.7.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.70.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.70.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.70.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.70.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.70.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.70.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.71.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.71.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.71.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.71.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.71.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.71.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.72.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.72.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.72.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.72.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.72.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.72.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.73.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.73.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.73.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.73.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.73.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.73.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.74.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.74.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.74.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.74.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.74.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.74.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.75.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.75.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.75.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.75.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.75.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.75.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.76.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.76.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.76.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.76.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.76.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.76.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.77.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.77.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.77.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.77.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.77.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.77.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.78.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.78.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.78.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.78.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.78.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.78.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.79.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.79.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.79.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.79.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.79.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.79.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.8.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.8.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.8.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.80.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.80.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.80.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.80.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.80.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.80.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.81.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.81.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.81.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.81.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.81.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.81.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.82.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.82.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.82.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.82.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.82.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.82.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.83.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.83.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.83.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.83.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.83.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.83.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.84.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.84.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.84.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.84.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.84.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.84.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.85.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.85.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.85.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.85.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.85.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.85.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.86.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.86.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.86.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.86.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.86.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.86.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.87.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.87.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.87.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.87.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.87.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.87.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.88.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.88.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.88.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.88.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.88.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.88.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.89.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.89.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.89.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.89.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.89.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.89.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.9.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.9.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.9.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.90.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.90.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.90.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.90.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.90.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.90.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.91.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.91.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.91.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.91.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.91.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.91.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.92.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.92.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.92.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.92.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.92.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.92.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.93.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.93.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.93.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.93.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.93.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.93.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.94.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.94.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.94.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.94.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.94.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.94.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.95.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.95.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.95.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.95.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.95.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.95.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.96.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.96.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.96.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.96.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.96.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.96.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.97.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.97.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.97.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.97.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.97.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.97.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.98.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.98.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.98.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.98.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.98.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.98.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.99.w1.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.99.w1.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.99.w2.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.99.w2.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.99.w3.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.experts.99.w3.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.shared_experts.down_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.shared_experts.gate_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.shared_experts.up_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.input_layernorm.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.post_attention_layernorm.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.index_k_norm.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.index_k_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.index_q_norm.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.index_q_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.k_norm.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.k_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.k_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.o_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.o_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.q_norm.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.q_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.q_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.v_proj.weight": "model-00006-of-00059.safetensors", - "language_model.model.layers.6.self_attn.v_proj.weight_scale": "model-00006-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.e_score_correction_bias": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.gate.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.0.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.0.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.0.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.1.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.1.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.1.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.10.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.10.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.10.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.10.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.10.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.10.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.100.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.100.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.100.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.100.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.100.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.100.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.101.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.101.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.101.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.101.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.101.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.101.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.102.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.102.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.102.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.102.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.102.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.102.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.103.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.103.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.103.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.103.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.103.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.103.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.104.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.104.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.104.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.104.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.104.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.104.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.105.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.105.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.105.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.105.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.105.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.105.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.106.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.106.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.106.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.106.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.106.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.106.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.107.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.107.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.107.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.107.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.107.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.107.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.108.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.108.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.108.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.108.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.108.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.108.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.109.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.109.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.109.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.109.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.109.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.109.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.11.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.11.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.11.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.11.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.11.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.11.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.110.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.110.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.110.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.110.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.110.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.110.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.111.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.111.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.111.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.111.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.111.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.111.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.112.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.112.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.112.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.112.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.112.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.112.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.113.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.113.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.113.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.113.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.113.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.113.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.114.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.114.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.114.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.114.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.114.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.114.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.115.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.115.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.115.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.115.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.115.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.115.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.116.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.116.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.116.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.116.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.116.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.116.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.117.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.117.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.117.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.117.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.117.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.117.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.118.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.118.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.118.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.118.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.118.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.118.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.119.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.119.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.119.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.119.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.119.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.119.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.12.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.12.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.12.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.12.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.12.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.12.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.120.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.120.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.120.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.120.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.120.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.120.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.121.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.121.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.121.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.121.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.121.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.121.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.122.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.122.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.122.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.122.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.122.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.122.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.123.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.123.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.123.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.123.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.123.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.123.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.124.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.124.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.124.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.124.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.124.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.124.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.125.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.125.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.125.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.125.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.125.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.125.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.126.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.126.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.126.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.126.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.126.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.126.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.127.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.127.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.127.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.127.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.127.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.127.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.13.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.13.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.13.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.13.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.13.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.13.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.14.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.14.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.14.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.14.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.14.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.14.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.15.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.15.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.15.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.15.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.15.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.15.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.16.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.16.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.16.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.16.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.16.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.16.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.17.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.17.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.17.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.17.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.17.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.17.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.18.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.18.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.18.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.18.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.18.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.18.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.19.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.19.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.19.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.19.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.19.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.19.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.2.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.2.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.2.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.20.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.20.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.20.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.20.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.20.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.20.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.21.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.21.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.21.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.21.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.21.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.21.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.22.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.22.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.22.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.22.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.22.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.22.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.23.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.23.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.23.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.23.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.23.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.23.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.24.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.24.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.24.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.24.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.24.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.24.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.25.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.25.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.25.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.25.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.25.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.25.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.26.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.26.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.26.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.26.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.26.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.26.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.27.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.27.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.27.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.27.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.27.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.27.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.28.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.28.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.28.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.28.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.28.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.28.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.29.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.29.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.29.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.29.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.29.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.29.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.3.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.3.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.3.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.30.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.30.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.30.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.30.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.30.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.30.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.31.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.31.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.31.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.31.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.31.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.31.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.32.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.32.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.32.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.32.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.32.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.32.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.33.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.33.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.33.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.33.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.33.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.33.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.34.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.34.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.34.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.34.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.34.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.34.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.35.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.35.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.35.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.35.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.35.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.35.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.36.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.36.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.36.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.36.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.36.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.36.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.37.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.37.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.37.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.37.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.37.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.37.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.38.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.38.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.38.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.38.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.38.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.38.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.39.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.39.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.39.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.39.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.39.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.39.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.4.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.4.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.4.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.40.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.40.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.40.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.40.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.40.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.40.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.41.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.41.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.41.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.41.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.41.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.41.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.42.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.42.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.42.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.42.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.42.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.42.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.43.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.43.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.43.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.43.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.43.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.43.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.44.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.44.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.44.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.44.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.44.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.44.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.45.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.45.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.45.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.45.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.45.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.45.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.46.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.46.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.46.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.46.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.46.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.46.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.47.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.47.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.47.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.47.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.47.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.47.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.48.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.48.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.48.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.48.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.48.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.48.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.49.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.49.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.49.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.49.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.49.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.49.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.5.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.5.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.5.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.50.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.50.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.50.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.50.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.50.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.50.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.51.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.51.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.51.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.51.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.51.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.51.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.52.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.52.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.52.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.52.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.52.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.52.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.53.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.53.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.53.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.53.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.53.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.53.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.54.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.54.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.54.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.54.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.54.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.54.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.55.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.55.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.55.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.55.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.55.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.55.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.56.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.56.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.56.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.56.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.56.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.56.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.57.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.57.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.57.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.57.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.57.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.57.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.58.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.58.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.58.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.58.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.58.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.58.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.59.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.59.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.59.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.59.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.59.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.59.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.6.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.6.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.6.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.60.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.60.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.60.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.60.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.60.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.60.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.61.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.61.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.61.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.61.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.61.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.61.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.62.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.62.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.62.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.62.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.62.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.62.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.63.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.63.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.63.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.63.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.63.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.63.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.64.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.64.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.64.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.64.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.64.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.64.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.65.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.65.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.65.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.65.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.65.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.65.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.66.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.66.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.66.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.66.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.66.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.66.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.67.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.67.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.67.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.67.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.67.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.67.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.68.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.68.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.68.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.68.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.68.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.68.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.69.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.69.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.69.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.69.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.69.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.69.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.7.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.7.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.7.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.70.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.70.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.70.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.70.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.70.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.70.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.71.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.71.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.71.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.71.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.71.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.71.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.72.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.72.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.72.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.72.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.72.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.72.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.73.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.73.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.73.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.73.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.73.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.73.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.74.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.74.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.74.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.74.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.74.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.74.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.75.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.75.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.75.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.75.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.75.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.75.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.76.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.76.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.76.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.76.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.76.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.76.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.77.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.77.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.77.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.77.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.77.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.77.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.78.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.78.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.78.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.78.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.78.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.78.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.79.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.79.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.79.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.79.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.79.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.79.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.8.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.8.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.8.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.8.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.8.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.8.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.80.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.80.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.80.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.80.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.80.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.80.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.81.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.81.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.81.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.81.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.81.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.81.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.82.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.82.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.82.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.82.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.82.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.82.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.83.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.83.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.83.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.83.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.83.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.83.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.84.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.84.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.84.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.84.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.84.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.84.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.85.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.85.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.85.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.85.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.85.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.85.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.86.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.86.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.86.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.86.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.86.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.86.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.87.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.87.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.87.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.87.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.87.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.87.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.88.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.88.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.88.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.88.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.88.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.88.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.89.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.89.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.89.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.89.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.89.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.89.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.9.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.9.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.9.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.9.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.9.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.9.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.90.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.90.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.90.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.90.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.90.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.90.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.91.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.91.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.91.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.91.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.91.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.91.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.92.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.92.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.92.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.92.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.92.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.92.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.93.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.93.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.93.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.93.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.93.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.93.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.94.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.94.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.94.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.94.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.94.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.94.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.95.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.95.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.95.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.95.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.95.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.95.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.96.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.96.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.96.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.96.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.96.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.96.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.97.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.97.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.97.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.97.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.97.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.97.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.98.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.98.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.98.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.98.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.98.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.98.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.99.w1.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.99.w1.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.99.w2.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.99.w2.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.99.w3.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.experts.99.w3.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.shared_experts.down_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.shared_experts.gate_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.shared_experts.up_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.input_layernorm.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.post_attention_layernorm.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.index_k_norm.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.index_k_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.index_q_norm.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.index_q_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.k_norm.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.k_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.k_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.o_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.o_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.q_norm.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.q_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.q_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.v_proj.weight": "model-00027-of-00059.safetensors", - "language_model.model.layers.27.self_attn.v_proj.weight_scale": "model-00027-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.gate.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.108.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.108.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.108.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.108.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.108.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.108.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.109.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.109.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.109.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.109.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.109.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.109.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.11.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.11.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.11.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.11.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.11.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.11.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.110.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.110.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.110.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.110.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.110.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.110.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.111.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.111.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.111.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.111.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.111.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.111.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.112.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.112.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.112.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.112.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.112.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.112.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.113.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.113.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.113.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.113.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.113.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.113.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.114.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.114.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.114.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.114.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.114.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.114.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.115.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.115.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.115.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.115.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.115.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.115.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.116.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.116.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.116.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.116.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.116.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.116.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.117.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.117.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.117.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.117.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.117.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.117.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.118.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.118.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.118.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.118.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.118.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.118.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.119.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.119.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.119.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.119.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.119.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.119.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.12.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.12.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.12.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.12.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.12.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.12.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.120.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.120.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.120.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.120.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.120.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.120.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.121.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.121.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.121.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.121.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.121.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.121.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.122.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.122.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.122.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.122.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.122.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.122.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.123.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.123.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.123.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.123.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.123.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.123.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.124.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.124.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.124.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.124.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.124.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.124.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.125.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.125.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.125.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.125.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.125.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.125.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.126.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.126.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.126.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.126.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.126.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.126.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.127.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.127.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.127.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.127.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.127.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.127.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.13.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.13.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.13.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.13.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.13.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.13.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.14.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.14.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.14.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.14.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.14.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.14.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.15.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.15.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.15.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.15.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.15.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.15.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.16.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.16.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.16.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.16.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.16.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.16.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.17.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.17.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.17.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.17.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.17.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.17.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.18.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.18.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.18.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.18.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.18.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.18.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.19.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.19.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.19.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.19.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.19.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.19.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.2.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.2.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.2.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.20.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.20.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.20.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.20.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.20.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.20.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.21.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.21.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.21.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.21.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.21.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.21.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.22.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.22.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.22.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.22.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.22.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.22.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.23.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.23.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.23.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.23.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.23.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.23.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.24.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.24.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.24.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.24.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.24.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.24.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.25.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.25.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.25.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.25.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.25.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.25.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.26.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.26.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.26.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.26.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.26.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.26.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.27.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.27.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.27.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.27.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.27.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.27.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.28.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.28.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.28.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.28.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.28.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.28.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.29.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.29.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.29.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.29.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.29.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.29.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.3.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.3.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.3.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.30.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.30.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.30.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.30.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.30.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.30.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.31.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.31.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.31.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.31.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.31.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.31.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.32.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.32.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.32.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.32.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.32.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.32.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.33.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.33.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.33.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.33.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.33.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.33.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.34.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.34.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.34.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.34.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.34.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.34.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.35.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.35.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.35.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.35.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.35.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.35.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.36.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.36.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.36.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.36.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.36.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.36.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.37.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.37.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.37.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.37.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.37.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.37.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.38.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.38.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.38.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.38.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.38.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.38.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.39.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.39.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.39.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.39.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.39.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.39.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.4.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.4.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.4.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.4.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.40.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.40.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.40.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.40.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.40.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.40.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.41.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.41.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.41.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.41.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.41.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.41.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.42.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.42.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.42.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.42.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.42.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.42.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.43.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.43.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.43.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.43.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.43.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.43.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.44.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.44.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.44.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.44.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.44.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.44.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.45.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.45.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.45.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.45.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.45.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.45.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.46.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.46.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.46.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.46.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.46.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.46.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.47.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.47.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.47.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.47.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.47.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.47.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.48.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.48.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.48.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.48.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.48.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.48.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.49.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.49.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.49.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.49.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.49.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.49.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.5.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.5.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.5.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.50.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.50.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.50.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.50.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.50.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.50.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.51.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.51.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.51.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.51.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.51.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.51.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.52.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.52.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.52.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.52.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.52.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.52.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.53.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.53.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.53.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.53.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.53.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.53.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.54.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.54.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.54.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.54.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.54.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.54.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.55.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.55.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.55.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.55.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.55.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.55.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.56.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.56.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.56.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.56.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.56.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.56.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.57.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.57.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.57.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.57.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.57.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.57.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.58.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.58.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.58.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.58.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.58.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.58.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.59.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.59.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.59.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.59.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.59.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.59.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.6.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.6.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.6.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.60.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.60.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.60.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.60.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.60.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.60.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.61.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.61.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.61.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.61.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.61.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.61.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.62.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.62.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.62.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.62.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.62.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.62.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.63.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.63.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.63.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.63.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.63.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.63.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.64.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.64.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.64.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.64.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.64.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.64.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.65.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.65.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.65.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.65.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.65.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.65.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.66.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.66.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.66.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.66.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.66.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.66.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.67.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.67.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.67.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.67.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.67.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.67.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.68.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.68.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.68.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.68.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.68.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.68.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.69.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.69.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.69.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.69.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.69.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.69.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.7.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.7.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.7.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.70.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.70.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.70.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.70.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.70.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.70.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.71.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.71.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.71.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.71.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.71.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.71.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.72.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.72.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.72.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.72.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.72.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.72.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.73.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.73.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.73.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.73.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.73.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.73.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.74.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.74.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.74.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.74.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.74.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.74.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.75.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.75.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.75.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.75.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.75.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.75.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.76.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.76.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.76.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.76.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.76.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.76.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.77.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.77.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.77.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.77.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.77.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.77.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.78.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.78.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.78.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.78.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.78.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.78.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.79.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.79.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.79.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.79.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.79.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.79.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.8.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.8.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.8.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.8.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.8.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.8.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.80.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.80.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.80.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.80.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.80.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.80.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.81.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.81.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.81.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.81.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.81.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.81.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.82.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.82.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.82.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.82.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.82.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.82.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.83.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.83.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.83.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.83.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.83.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.83.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.84.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.84.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.84.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.84.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.84.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.84.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.85.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.85.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.85.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.85.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.85.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.85.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.86.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.86.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.86.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.86.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.86.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.86.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.87.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.87.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.87.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.87.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.87.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.87.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.88.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.88.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.88.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.88.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.88.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.88.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.89.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.89.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.89.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.89.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.89.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.89.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.9.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.9.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.9.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.9.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.9.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.9.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.90.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.90.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.90.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.90.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.90.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.90.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.91.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.91.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.91.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.91.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.91.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.91.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.92.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.92.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.92.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.92.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.92.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.92.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.93.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.93.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.93.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.93.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.93.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.93.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.94.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.94.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.94.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.94.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.94.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.94.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.95.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.95.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.95.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.95.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.95.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.95.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.96.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.96.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.96.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.96.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.96.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.96.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.97.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.97.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.97.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.97.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.97.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.97.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.98.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.98.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.98.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.98.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.98.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.98.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.99.w1.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.99.w1.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.99.w2.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.99.w2.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.99.w3.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.experts.99.w3.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.shared_experts.down_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.shared_experts.gate_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.shared_experts.up_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.input_layernorm.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.post_attention_layernorm.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.index_k_norm.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.index_k_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.index_q_norm.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.index_q_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.k_norm.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.k_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.k_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.o_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.o_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.q_norm.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.q_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.q_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.v_proj.weight": "model-00039-of-00059.safetensors", - "language_model.model.layers.39.self_attn.v_proj.weight_scale": "model-00039-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.e_score_correction_bias": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.gate.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.e_score_correction_bias": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.0.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.0.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.0.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.1.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.1.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.1.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.10.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.10.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.10.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.10.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.10.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.10.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.100.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.100.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.100.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.100.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.100.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.100.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.101.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.101.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.101.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.101.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.101.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.101.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.102.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.102.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.102.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.102.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.102.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.102.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.103.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.103.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.103.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.103.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.103.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.103.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.104.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.104.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.104.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.104.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.104.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.104.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.105.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.105.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.105.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.105.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.105.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.105.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.106.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.106.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.106.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.106.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.106.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.106.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.107.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.107.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.107.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.107.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.107.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.107.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.108.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.108.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.108.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.108.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.108.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.108.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.109.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.109.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.109.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.109.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.109.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.109.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.11.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.11.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.11.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.11.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.11.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.11.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.110.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.110.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.110.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.110.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.110.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.110.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.111.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.111.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.111.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.111.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.111.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.111.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.112.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.112.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.112.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.112.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.112.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.112.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.113.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.113.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.113.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.113.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.113.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.113.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.114.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.114.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.114.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.114.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.114.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.114.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.115.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.115.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.115.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.115.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.115.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.115.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.116.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.116.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.116.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.116.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.116.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.116.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.117.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.117.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.117.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.117.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.117.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.117.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.118.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.118.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.118.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.118.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.118.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.118.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.119.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.119.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.119.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.119.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.119.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.119.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.12.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.12.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.12.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.12.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.12.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.12.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.120.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.120.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.120.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.120.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.120.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.120.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.121.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.121.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.121.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.121.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.121.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.121.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.122.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.122.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.122.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.122.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.122.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.122.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.123.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.123.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.123.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.123.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.123.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.123.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.124.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.124.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.124.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.124.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.124.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.124.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.125.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.125.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.125.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.125.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.125.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.125.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.126.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.126.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.126.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.126.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.126.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.126.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.127.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.127.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.127.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.127.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.127.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.127.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.13.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.13.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.13.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.13.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.13.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.13.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.14.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.14.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.14.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.14.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.14.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.14.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.15.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.15.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.15.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.15.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.15.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.15.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.16.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.16.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.16.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.16.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.16.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.16.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.17.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.17.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.17.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.17.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.17.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.17.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.18.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.18.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.18.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.18.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.18.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.18.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.19.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.19.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.19.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.19.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.19.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.19.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.2.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.2.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.2.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.20.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.20.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.20.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.20.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.20.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.20.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.21.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.21.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.21.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.21.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.21.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.21.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.22.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.22.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.22.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.22.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.22.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.22.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.23.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.23.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.23.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.23.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.23.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.23.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.24.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.24.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.24.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.24.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.24.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.24.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.25.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.25.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.25.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.25.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.25.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.25.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.26.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.26.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.26.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.26.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.26.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.26.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.27.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.27.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.27.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.27.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.27.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.27.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.28.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.28.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.28.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.28.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.28.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.28.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.29.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.29.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.29.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.29.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.29.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.29.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.3.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.3.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.3.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.30.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.30.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.30.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.30.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.30.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.30.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.31.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.31.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.31.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.31.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.31.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.31.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.32.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.32.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.32.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.32.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.32.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.32.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.33.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.33.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.33.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.33.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.33.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.33.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.34.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.34.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.34.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.34.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.34.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.34.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.35.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.35.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.35.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.35.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.35.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.35.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.36.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.36.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.36.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.36.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.36.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.36.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.37.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.37.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.37.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.37.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.37.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.37.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.38.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.38.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.38.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.38.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.38.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.38.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.39.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.39.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.39.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.39.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.39.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.39.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.4.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.4.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.4.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.40.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.40.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.40.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.40.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.40.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.40.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.41.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.41.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.41.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.41.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.41.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.41.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.42.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.42.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.42.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.42.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.42.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.42.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.43.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.43.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.43.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.43.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.43.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.43.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.44.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.44.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.44.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.44.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.44.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.44.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.45.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.45.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.45.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.45.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.45.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.45.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.46.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.46.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.46.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.46.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.46.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.46.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.47.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.47.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.47.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.47.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.47.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.47.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.48.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.48.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.48.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.48.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.48.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.48.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.49.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.49.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.49.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.49.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.49.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.49.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.5.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.5.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.5.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.50.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.50.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.50.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.50.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.50.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.50.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.51.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.51.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.51.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.51.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.51.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.51.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.52.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.52.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.52.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.52.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.52.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.52.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.53.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.53.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.53.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.53.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.53.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.53.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.54.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.54.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.54.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.54.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.54.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.54.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.55.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.55.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.55.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.55.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.55.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.55.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.56.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.56.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.56.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.56.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.56.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.56.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.57.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.57.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.57.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.57.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.57.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.57.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.58.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.58.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.58.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.58.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.58.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.58.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.59.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.59.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.59.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.59.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.59.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.59.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.6.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.6.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.6.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.60.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.60.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.60.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.60.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.60.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.60.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.61.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.61.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.61.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.61.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.61.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.61.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.62.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.62.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.62.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.62.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.62.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.62.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.63.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.63.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.63.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.63.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.63.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.63.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.64.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.64.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.64.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.64.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.64.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.64.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.65.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.65.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.65.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.65.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.65.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.65.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.66.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.66.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.66.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.66.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.66.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.66.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.67.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.67.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.67.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.67.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.67.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.67.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.68.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.68.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.68.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.68.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.68.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.68.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.69.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.69.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.69.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.69.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.69.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.69.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.7.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.7.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.7.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.70.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.70.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.70.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.70.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.70.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.70.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.71.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.71.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.71.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.71.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.71.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.71.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.72.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.72.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.72.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.72.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.72.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.72.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.73.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.73.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.73.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.73.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.73.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.73.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.74.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.74.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.74.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.74.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.74.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.74.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.75.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.75.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.75.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.75.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.75.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.75.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.76.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.76.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.76.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.76.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.76.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.76.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.77.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.77.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.77.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.77.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.77.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.77.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.78.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.78.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.78.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.78.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.78.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.78.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.79.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.79.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.79.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.79.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.79.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.79.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.8.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.8.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.8.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.8.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.8.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.8.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.80.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.80.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.80.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.80.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.80.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.80.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.81.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.81.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.81.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.81.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.81.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.81.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.82.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.82.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.82.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.82.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.82.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.82.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.83.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.83.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.83.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.83.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.83.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.83.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.84.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.84.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.84.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.84.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.84.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.84.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.85.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.85.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.85.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.85.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.85.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.85.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.86.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.86.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.86.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.86.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.86.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.86.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.87.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.87.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.87.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.87.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.87.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.87.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.88.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.88.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.88.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.88.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.88.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.88.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.89.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.89.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.89.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.89.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.89.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.89.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.9.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.9.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.9.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.9.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.9.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.9.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.90.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.90.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.90.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.90.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.90.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.90.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.91.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.91.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.91.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.91.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.91.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.91.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.92.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.92.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.92.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.92.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.92.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.92.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.93.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.93.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.93.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.93.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.93.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.93.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.94.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.94.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.94.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.94.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.94.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.94.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.95.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.95.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.95.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.95.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.95.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.95.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.96.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.96.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.96.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.96.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.96.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.96.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.97.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.97.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.97.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.97.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.97.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.97.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.98.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.98.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.98.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.98.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.98.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.98.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.99.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.99.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.99.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.99.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.99.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.experts.99.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.shared_experts.down_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.shared_experts.gate_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.shared_experts.up_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.input_layernorm.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.post_attention_layernorm.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.index_k_norm.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.index_k_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.index_q_norm.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.index_q_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.k_norm.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.k_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.k_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.o_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.o_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.q_norm.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.q_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.q_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.v_proj.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.23.self_attn.v_proj.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.0.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.0.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.0.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.1.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.1.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.1.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.10.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.10.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.10.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.10.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.10.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.10.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.100.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.100.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.100.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.100.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.100.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.100.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.101.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.101.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.101.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.101.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.101.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.101.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.102.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.102.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.102.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.102.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.102.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.102.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.103.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.103.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.103.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.103.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.103.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.103.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.104.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.104.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.104.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.104.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.104.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.104.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.105.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.105.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.105.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.105.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.105.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.105.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.106.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.106.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.106.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.106.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.106.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.106.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.107.w1.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.107.w1.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.107.w2.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.107.w2.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.107.w3.weight": "model-00023-of-00059.safetensors", - "language_model.model.layers.57.block_sparse_moe.experts.107.w3.weight_scale": "model-00023-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.e_score_correction_bias": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.gate.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.0.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.0.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.0.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.1.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.1.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.1.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.10.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.10.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.10.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.10.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.10.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.10.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.100.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.100.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.100.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.100.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.100.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.100.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.101.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.101.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.101.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.101.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.101.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.101.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.102.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.102.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.102.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.102.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.102.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.102.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.103.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.103.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.103.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.103.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.103.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.103.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.104.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.104.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.104.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.104.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.104.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.104.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.105.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.105.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.105.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.105.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.105.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.105.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.106.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.106.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.106.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.106.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.106.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.106.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.107.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.107.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.107.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.107.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.107.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.107.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.108.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.108.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.108.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.108.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.108.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.108.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.109.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.109.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.109.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.109.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.109.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.109.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.11.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.11.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.11.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.11.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.11.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.11.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.110.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.110.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.110.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.110.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.110.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.110.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.111.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.111.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.111.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.111.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.111.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.111.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.112.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.112.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.112.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.112.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.112.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.112.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.113.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.113.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.113.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.113.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.113.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.113.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.114.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.114.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.114.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.114.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.114.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.114.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.115.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.115.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.115.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.115.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.115.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.115.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.116.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.116.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.116.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.116.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.116.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.116.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.117.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.117.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.117.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.117.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.117.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.117.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.118.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.118.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.118.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.118.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.118.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.118.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.119.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.119.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.119.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.119.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.119.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.119.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.12.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.12.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.12.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.12.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.12.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.12.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.120.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.120.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.120.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.120.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.120.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.120.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.121.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.121.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.121.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.121.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.121.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.121.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.122.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.122.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.122.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.122.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.122.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.122.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.123.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.123.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.123.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.123.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.123.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.123.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.124.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.124.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.124.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.124.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.124.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.124.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.125.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.125.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.125.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.125.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.125.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.125.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.126.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.126.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.126.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.126.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.126.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.126.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.127.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.127.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.127.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.127.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.127.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.127.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.13.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.13.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.13.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.13.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.13.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.13.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.14.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.14.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.14.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.14.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.14.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.14.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.15.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.15.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.15.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.15.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.15.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.15.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.16.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.16.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.16.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.16.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.16.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.16.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.17.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.17.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.17.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.17.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.17.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.17.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.18.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.18.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.18.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.18.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.18.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.18.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.19.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.19.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.19.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.19.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.19.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.19.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.2.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.2.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.2.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.20.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.20.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.20.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.20.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.20.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.20.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.21.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.21.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.21.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.21.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.21.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.21.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.22.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.22.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.22.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.22.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.22.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.22.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.23.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.23.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.23.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.23.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.23.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.23.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.24.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.24.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.24.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.24.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.24.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.24.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.25.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.25.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.25.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.25.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.25.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.25.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.26.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.26.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.26.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.26.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.26.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.26.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.27.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.27.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.27.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.27.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.27.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.27.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.28.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.28.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.28.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.28.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.28.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.28.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.29.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.29.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.29.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.29.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.29.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.29.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.3.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.3.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.3.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.30.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.30.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.30.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.30.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.30.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.30.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.31.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.31.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.31.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.31.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.31.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.31.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.32.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.32.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.32.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.32.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.32.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.32.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.33.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.33.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.33.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.33.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.33.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.33.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.34.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.34.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.34.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.34.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.34.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.34.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.35.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.35.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.35.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.35.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.35.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.35.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.36.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.36.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.36.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.36.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.36.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.36.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.37.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.37.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.37.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.37.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.37.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.37.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.38.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.38.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.38.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.38.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.38.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.38.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.39.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.39.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.39.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.39.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.39.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.39.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.4.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.4.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.4.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.40.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.40.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.40.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.40.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.40.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.40.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.41.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.41.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.41.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.41.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.41.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.41.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.42.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.42.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.42.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.42.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.42.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.42.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.43.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.43.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.43.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.43.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.43.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.43.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.44.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.44.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.44.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.44.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.44.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.44.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.45.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.45.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.45.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.45.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.45.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.45.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.46.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.46.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.46.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.46.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.46.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.46.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.47.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.47.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.47.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.47.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.47.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.47.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.48.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.48.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.48.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.48.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.48.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.48.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.49.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.49.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.49.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.49.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.49.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.49.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.5.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.5.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.5.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.50.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.50.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.50.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.50.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.50.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.50.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.51.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.51.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.51.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.51.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.51.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.51.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.52.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.52.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.52.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.52.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.52.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.52.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.53.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.53.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.53.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.53.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.53.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.53.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.54.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.54.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.54.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.54.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.54.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.54.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.55.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.55.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.55.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.55.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.55.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.55.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.56.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.56.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.56.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.56.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.56.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.56.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.57.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.57.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.57.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.57.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.57.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.57.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.58.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.58.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.58.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.58.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.58.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.58.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.59.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.59.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.59.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.59.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.59.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.59.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.6.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.6.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.6.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.60.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.60.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.60.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.60.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.60.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.60.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.61.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.61.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.61.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.61.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.61.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.61.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.62.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.62.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.62.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.62.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.62.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.62.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.63.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.63.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.63.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.63.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.63.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.63.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.64.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.64.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.64.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.64.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.64.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.64.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.65.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.65.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.65.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.65.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.65.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.65.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.66.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.66.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.66.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.66.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.66.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.66.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.67.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.67.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.67.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.67.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.67.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.67.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.68.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.68.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.68.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.68.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.68.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.68.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.69.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.69.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.69.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.69.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.69.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.69.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.7.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.7.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.7.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.70.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.70.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.70.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.70.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.70.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.70.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.71.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.71.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.71.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.71.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.71.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.71.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.72.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.72.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.72.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.72.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.72.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.72.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.73.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.73.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.73.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.73.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.73.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.73.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.74.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.74.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.74.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.74.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.74.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.74.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.75.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.75.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.75.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.75.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.75.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.75.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.76.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.76.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.76.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.76.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.76.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.76.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.77.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.77.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.77.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.77.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.77.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.77.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.78.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.78.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.78.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.78.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.78.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.78.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.79.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.79.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.79.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.79.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.79.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.79.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.8.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.8.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.8.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.8.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.8.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.8.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.80.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.80.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.80.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.80.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.80.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.80.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.81.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.81.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.81.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.81.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.81.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.81.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.82.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.82.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.82.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.82.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.82.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.82.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.83.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.83.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.83.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.83.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.83.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.83.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.84.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.84.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.84.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.84.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.84.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.84.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.85.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.85.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.85.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.85.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.85.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.85.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.86.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.86.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.86.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.86.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.86.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.86.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.87.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.87.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.87.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.87.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.87.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.87.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.88.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.88.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.88.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.88.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.88.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.88.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.89.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.89.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.89.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.89.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.89.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.89.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.9.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.9.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.9.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.9.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.9.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.9.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.90.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.90.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.90.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.90.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.90.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.90.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.91.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.91.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.91.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.91.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.91.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.91.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.92.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.92.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.92.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.92.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.92.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.92.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.93.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.93.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.93.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.93.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.93.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.93.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.94.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.94.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.94.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.94.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.94.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.94.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.95.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.95.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.95.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.95.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.95.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.95.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.96.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.96.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.96.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.96.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.96.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.96.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.97.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.97.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.97.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.97.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.97.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.97.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.98.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.98.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.98.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.98.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.98.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.98.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.99.w1.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.99.w1.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.99.w2.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.99.w2.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.99.w3.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.experts.99.w3.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.shared_experts.down_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.shared_experts.gate_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.shared_experts.up_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.input_layernorm.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.post_attention_layernorm.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.index_k_norm.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.index_k_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.index_q_norm.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.index_q_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.k_norm.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.k_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.k_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.o_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.o_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.q_norm.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.q_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.q_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.v_proj.weight": "model-00030-of-00059.safetensors", - "language_model.model.layers.30.self_attn.v_proj.weight_scale": "model-00030-of-00059.safetensors", - "language_model.lm_head.weight": "model-00001-of-00059.safetensors", - "language_model.model.embed_tokens.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00059.safetensors", - "language_model.model.norm.weight": "model-00001-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.e_score_correction_bias": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.gate.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.0.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.0.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.0.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.1.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.1.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.1.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.10.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.10.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.10.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.10.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.10.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.10.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.100.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.100.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.100.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.100.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.100.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.100.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.101.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.101.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.101.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.101.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.101.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.101.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.102.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.102.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.102.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.102.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.102.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.102.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.103.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.103.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.103.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.103.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.103.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.103.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.104.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.104.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.104.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.104.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.104.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.104.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.105.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.105.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.105.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.105.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.105.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.105.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.106.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.106.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.106.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.106.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.106.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.106.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.107.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.107.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.107.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.107.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.107.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.107.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.108.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.108.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.108.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.108.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.108.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.108.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.109.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.109.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.109.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.109.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.109.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.109.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.11.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.11.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.11.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.11.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.11.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.11.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.110.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.110.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.110.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.110.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.110.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.110.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.111.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.111.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.111.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.111.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.111.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.111.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.112.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.112.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.112.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.112.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.112.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.112.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.113.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.113.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.113.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.113.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.113.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.113.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.114.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.114.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.114.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.114.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.114.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.114.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.115.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.115.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.115.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.115.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.115.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.115.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.116.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.116.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.116.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.116.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.116.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.116.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.117.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.117.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.117.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.117.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.117.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.117.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.118.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.118.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.118.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.118.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.118.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.118.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.119.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.119.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.119.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.119.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.119.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.119.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.12.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.12.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.12.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.12.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.12.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.12.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.120.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.120.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.120.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.120.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.120.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.120.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.121.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.121.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.121.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.121.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.121.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.121.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.122.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.122.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.122.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.122.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.122.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.122.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.123.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.123.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.123.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.123.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.123.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.123.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.124.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.124.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.124.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.124.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.124.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.124.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.125.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.125.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.125.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.125.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.125.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.125.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.126.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.126.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.126.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.126.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.126.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.126.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.127.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.127.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.127.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.127.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.127.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.127.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.13.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.13.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.13.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.13.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.13.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.13.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.14.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.14.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.14.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.14.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.14.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.14.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.15.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.15.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.15.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.15.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.15.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.15.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.16.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.16.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.16.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.16.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.16.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.16.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.17.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.17.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.17.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.17.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.17.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.17.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.18.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.18.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.18.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.18.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.18.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.18.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.19.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.19.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.19.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.19.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.19.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.19.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.2.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.2.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.2.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.20.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.20.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.20.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.20.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.20.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.20.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.21.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.21.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.21.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.21.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.21.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.21.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.22.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.22.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.22.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.22.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.22.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.22.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.23.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.23.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.23.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.23.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.23.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.23.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.24.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.24.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.24.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.24.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.24.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.24.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.25.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.25.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.25.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.25.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.25.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.25.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.26.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.26.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.26.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.26.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.26.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.26.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.27.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.27.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.27.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.27.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.27.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.27.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.28.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.28.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.28.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.28.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.28.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.28.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.29.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.29.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.29.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.29.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.29.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.29.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.3.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.3.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.3.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.30.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.30.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.30.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.30.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.30.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.30.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.31.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.31.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.31.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.31.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.31.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.31.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.32.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.32.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.32.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.32.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.32.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.32.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.33.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.33.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.33.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.33.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.33.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.33.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.34.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.34.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.34.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.34.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.34.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.34.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.35.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.35.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.35.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.35.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.35.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.35.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.36.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.36.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.36.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.36.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.36.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.36.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.37.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.37.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.37.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.37.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.37.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.37.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.38.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.38.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.38.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.38.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.38.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.38.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.39.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.39.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.39.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.39.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.39.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.39.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.4.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.4.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.4.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.40.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.40.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.40.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.40.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.40.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.40.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.41.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.41.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.41.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.41.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.41.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.41.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.42.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.42.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.42.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.42.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.42.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.42.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.43.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.43.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.43.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.43.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.43.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.43.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.44.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.44.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.44.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.44.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.44.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.44.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.45.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.45.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.45.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.45.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.45.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.45.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.46.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.46.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.46.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.46.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.46.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.46.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.47.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.47.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.47.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.47.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.47.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.47.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.48.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.48.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.48.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.48.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.48.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.48.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.49.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.49.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.49.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.49.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.49.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.49.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.5.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.5.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.5.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.50.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.50.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.50.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.50.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.50.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.50.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.51.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.51.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.51.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.51.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.51.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.51.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.52.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.52.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.52.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.52.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.52.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.52.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.53.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.53.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.53.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.53.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.53.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.53.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.54.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.54.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.54.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.54.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.54.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.54.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.55.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.55.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.55.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.55.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.55.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.55.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.56.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.56.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.56.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.56.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.56.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.56.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.57.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.57.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.57.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.57.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.57.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.57.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.58.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.58.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.58.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.58.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.58.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.58.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.59.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.59.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.59.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.59.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.59.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.59.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.6.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.6.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.6.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.60.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.60.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.60.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.60.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.60.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.60.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.61.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.61.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.61.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.61.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.61.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.61.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.62.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.62.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.62.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.62.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.62.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.62.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.63.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.63.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.63.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.63.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.63.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.63.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.64.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.64.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.64.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.64.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.64.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.64.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.65.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.65.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.65.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.65.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.65.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.65.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.66.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.66.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.66.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.66.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.66.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.66.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.67.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.67.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.67.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.67.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.67.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.67.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.68.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.68.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.68.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.68.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.68.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.68.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.69.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.69.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.69.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.69.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.69.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.69.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.7.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.7.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.7.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.70.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.70.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.70.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.70.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.70.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.70.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.71.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.71.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.71.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.71.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.71.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.71.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.72.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.72.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.72.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.72.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.72.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.72.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.73.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.73.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.73.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.73.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.73.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.73.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.74.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.74.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.74.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.74.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.74.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.74.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.75.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.75.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.75.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.75.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.75.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.75.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.76.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.76.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.76.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.76.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.76.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.76.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.77.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.77.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.77.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.77.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.77.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.77.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.78.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.78.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.78.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.78.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.78.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.78.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.79.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.79.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.79.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.79.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.79.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.79.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.8.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.8.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.8.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.8.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.8.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.8.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.80.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.80.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.80.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.80.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.80.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.80.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.81.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.81.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.81.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.81.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.81.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.81.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.82.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.82.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.82.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.82.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.82.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.82.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.83.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.83.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.83.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.83.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.83.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.83.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.84.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.84.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.84.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.84.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.84.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.84.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.85.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.85.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.85.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.85.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.85.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.85.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.86.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.86.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.86.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.86.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.86.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.86.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.87.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.87.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.87.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.87.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.87.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.87.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.88.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.88.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.88.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.88.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.88.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.88.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.89.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.89.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.89.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.89.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.89.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.89.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.9.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.9.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.9.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.9.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.9.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.9.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.90.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.90.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.90.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.90.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.90.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.90.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.91.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.91.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.91.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.91.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.91.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.91.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.92.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.92.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.92.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.92.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.92.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.92.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.93.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.93.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.93.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.93.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.93.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.93.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.94.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.94.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.94.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.94.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.94.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.94.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.95.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.95.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.95.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.95.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.95.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.95.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.96.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.96.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.96.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.96.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.96.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.96.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.97.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.97.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.97.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.97.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.97.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.97.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.98.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.98.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.98.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.98.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.98.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.98.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.99.w1.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.99.w1.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.99.w2.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.99.w2.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.99.w3.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.experts.99.w3.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.shared_experts.down_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.shared_experts.gate_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.shared_experts.up_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.input_layernorm.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.post_attention_layernorm.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.index_k_norm.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.index_k_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.index_q_norm.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.index_q_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.k_norm.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.k_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.k_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.o_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.o_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.q_norm.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.q_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.q_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.v_proj.weight": "model-00032-of-00059.safetensors", - "language_model.model.layers.32.self_attn.v_proj.weight_scale": "model-00032-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.gate.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.108.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.108.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.108.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.108.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.108.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.108.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.109.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.109.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.109.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.109.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.109.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.109.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.11.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.11.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.11.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.11.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.11.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.11.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.110.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.110.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.110.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.110.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.110.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.110.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.111.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.111.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.111.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.111.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.111.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.111.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.112.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.112.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.112.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.112.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.112.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.112.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.113.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.113.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.113.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.113.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.113.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.113.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.114.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.114.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.114.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.114.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.114.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.114.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.115.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.115.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.115.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.115.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.115.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.115.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.116.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.116.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.116.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.116.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.116.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.116.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.117.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.117.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.117.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.117.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.117.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.117.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.118.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.118.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.118.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.118.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.118.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.118.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.119.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.119.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.119.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.119.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.119.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.119.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.12.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.12.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.12.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.12.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.12.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.12.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.120.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.120.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.120.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.120.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.120.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.120.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.121.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.121.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.121.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.121.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.121.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.121.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.122.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.122.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.122.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.122.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.122.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.122.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.123.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.123.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.123.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.123.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.123.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.123.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.124.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.124.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.124.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.124.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.124.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.124.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.125.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.125.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.125.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.125.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.125.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.125.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.126.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.126.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.126.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.126.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.126.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.126.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.127.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.127.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.127.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.127.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.127.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.127.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.13.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.13.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.13.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.13.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.13.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.13.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.14.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.14.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.14.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.14.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.14.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.14.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.15.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.15.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.15.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.15.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.15.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.15.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.16.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.16.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.16.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.16.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.16.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.16.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.17.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.17.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.17.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.17.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.17.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.17.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.18.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.18.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.18.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.18.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.18.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.18.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.19.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.19.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.19.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.19.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.19.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.19.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.2.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.2.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.2.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.20.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.20.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.20.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.20.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.20.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.20.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.21.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.21.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.21.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.21.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.21.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.21.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.22.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.22.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.22.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.22.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.22.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.22.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.23.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.23.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.23.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.23.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.23.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.23.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.24.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.24.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.24.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.24.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.24.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.24.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.25.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.25.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.25.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.25.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.25.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.25.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.26.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.26.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.26.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.26.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.26.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.26.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.27.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.27.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.27.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.27.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.27.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.27.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.28.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.28.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.28.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.28.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.28.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.28.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.29.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.29.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.29.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.29.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.29.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.29.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.3.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.3.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.3.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.30.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.30.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.30.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.30.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.30.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.30.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.31.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.31.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.31.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.31.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.31.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.31.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.32.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.32.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.32.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.32.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.32.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.32.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.33.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.33.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.33.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.33.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.33.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.33.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.34.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.34.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.34.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.34.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.34.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.34.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.35.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.35.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.35.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.35.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.35.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.35.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.36.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.36.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.36.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.36.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.36.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.36.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.37.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.37.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.37.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.37.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.37.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.37.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.38.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.38.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.38.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.38.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.38.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.38.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.39.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.39.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.39.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.39.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.39.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.39.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.4.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.4.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.4.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.40.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.40.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.40.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.40.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.40.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.40.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.41.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.41.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.41.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.41.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.41.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.41.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.42.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.42.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.42.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.42.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.42.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.42.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.43.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.43.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.43.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.43.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.43.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.43.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.44.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.44.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.44.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.44.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.44.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.44.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.45.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.45.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.45.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.45.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.45.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.45.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.46.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.46.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.46.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.46.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.46.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.46.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.47.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.47.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.47.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.47.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.47.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.47.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.48.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.48.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.48.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.48.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.48.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.48.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.49.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.49.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.49.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.49.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.49.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.49.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.5.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.5.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.5.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.50.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.50.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.50.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.50.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.50.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.50.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.51.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.51.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.51.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.51.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.51.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.51.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.52.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.52.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.52.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.52.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.52.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.52.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.53.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.53.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.53.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.53.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.53.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.53.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.54.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.54.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.54.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.54.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.54.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.54.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.55.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.55.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.55.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.55.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.55.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.55.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.56.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.56.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.56.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.56.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.56.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.56.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.57.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.57.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.57.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.57.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.57.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.57.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.58.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.58.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.58.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.58.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.58.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.58.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.59.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.59.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.59.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.59.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.59.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.59.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.6.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.6.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.6.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.60.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.60.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.60.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.60.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.60.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.60.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.61.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.61.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.61.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.61.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.61.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.61.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.62.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.62.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.62.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.62.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.62.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.62.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.63.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.63.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.63.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.63.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.63.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.63.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.64.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.64.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.64.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.64.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.64.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.64.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.65.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.65.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.65.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.65.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.65.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.65.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.66.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.66.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.66.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.66.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.66.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.66.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.67.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.67.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.67.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.67.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.67.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.67.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.68.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.68.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.68.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.68.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.68.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.68.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.69.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.69.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.69.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.69.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.69.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.69.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.7.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.7.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.7.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.7.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.7.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.70.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.70.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.70.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.70.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.70.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.70.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.71.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.71.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.71.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.71.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.71.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.71.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.72.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.72.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.72.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.72.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.72.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.72.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.73.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.73.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.73.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.73.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.73.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.73.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.74.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.74.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.74.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.74.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.74.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.74.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.75.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.75.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.75.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.75.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.75.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.75.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.76.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.76.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.76.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.76.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.76.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.76.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.77.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.77.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.77.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.77.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.77.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.77.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.78.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.78.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.78.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.78.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.78.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.78.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.79.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.79.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.79.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.79.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.79.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.79.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.8.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.8.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.8.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.8.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.8.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.8.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.80.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.80.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.80.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.80.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.80.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.80.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.81.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.81.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.81.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.81.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.81.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.81.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.82.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.82.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.82.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.82.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.82.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.82.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.83.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.83.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.83.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.83.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.83.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.83.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.84.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.84.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.84.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.84.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.84.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.84.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.85.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.85.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.85.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.85.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.85.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.85.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.86.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.86.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.86.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.86.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.86.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.86.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.87.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.87.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.87.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.87.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.87.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.87.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.88.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.88.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.88.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.88.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.88.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.88.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.89.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.89.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.89.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.89.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.89.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.89.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.9.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.9.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.9.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.9.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.9.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.9.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.90.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.90.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.90.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.90.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.90.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.90.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.91.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.91.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.91.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.91.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.91.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.91.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.92.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.92.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.92.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.92.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.92.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.92.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.93.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.93.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.93.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.93.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.93.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.93.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.94.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.94.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.94.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.94.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.94.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.94.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.95.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.95.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.95.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.95.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.95.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.95.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.96.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.96.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.96.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.96.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.96.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.96.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.97.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.97.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.97.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.97.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.97.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.97.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.98.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.98.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.98.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.98.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.98.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.98.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.99.w1.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.99.w1.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.99.w2.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.99.w2.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.99.w3.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.99.w3.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.shared_experts.down_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.shared_experts.gate_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.shared_experts.up_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.input_layernorm.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.post_attention_layernorm.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.index_k_norm.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.index_k_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.index_q_norm.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.index_q_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.k_norm.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.k_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.k_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.o_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.o_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.q_norm.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.q_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.q_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.v_proj.weight": "model-00041-of-00059.safetensors", - "language_model.model.layers.41.self_attn.v_proj.weight_scale": "model-00041-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.gate.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.108.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.108.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.108.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.108.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.108.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.108.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.109.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.109.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.109.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.109.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.109.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.109.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.11.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.11.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.11.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.11.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.11.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.11.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.110.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.110.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.110.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.110.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.110.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.110.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.111.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.111.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.111.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.111.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.111.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.111.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.112.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.112.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.112.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.112.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.112.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.112.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.113.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.113.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.113.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.113.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.113.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.113.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.114.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.114.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.114.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.114.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.114.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.114.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.115.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.115.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.115.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.115.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.115.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.115.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.116.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.116.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.116.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.116.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.116.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.116.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.117.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.117.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.117.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.117.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.117.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.117.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.118.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.118.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.118.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.118.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.118.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.118.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.119.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.119.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.119.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.119.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.119.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.119.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.12.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.12.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.12.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.12.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.12.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.12.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.120.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.120.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.120.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.120.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.120.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.120.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.121.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.121.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.121.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.121.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.121.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.121.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.122.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.122.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.122.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.122.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.122.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.122.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.123.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.123.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.123.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.123.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.123.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.123.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.124.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.124.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.124.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.124.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.124.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.124.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.125.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.125.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.125.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.125.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.125.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.125.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.126.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.126.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.126.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.126.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.126.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.126.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.127.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.127.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.127.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.127.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.127.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.127.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.13.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.13.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.13.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.13.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.13.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.13.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.14.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.14.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.14.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.14.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.14.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.14.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.15.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.15.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.15.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.15.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.15.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.15.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.16.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.16.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.16.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.16.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.16.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.16.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.17.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.17.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.17.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.17.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.17.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.17.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.18.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.18.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.18.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.18.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.18.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.18.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.19.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.19.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.19.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.19.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.19.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.19.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.2.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.2.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.2.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.20.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.20.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.20.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.20.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.20.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.20.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.21.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.21.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.21.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.21.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.21.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.21.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.22.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.22.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.22.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.22.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.22.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.22.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.23.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.23.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.23.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.23.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.23.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.23.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.24.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.24.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.24.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.24.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.24.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.24.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.25.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.25.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.25.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.25.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.25.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.25.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.26.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.26.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.26.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.26.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.26.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.26.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.27.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.27.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.27.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.27.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.27.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.27.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.28.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.28.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.28.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.28.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.28.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.28.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.29.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.29.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.29.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.29.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.29.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.29.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.3.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.3.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.3.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.3.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.3.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.3.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.30.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.30.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.30.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.30.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.30.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.30.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.31.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.31.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.31.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.31.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.31.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.31.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.32.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.32.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.32.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.32.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.32.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.32.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.33.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.33.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.33.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.33.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.33.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.33.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.34.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.34.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.34.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.34.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.34.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.34.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.35.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.35.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.35.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.35.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.35.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.35.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.36.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.36.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.36.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.36.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.36.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.36.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.37.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.37.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.37.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.37.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.37.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.37.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.38.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.38.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.38.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.38.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.38.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.38.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.39.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.39.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.39.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.39.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.39.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.39.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.4.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.4.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.4.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.4.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.4.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.4.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.40.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.40.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.40.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.40.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.40.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.40.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.41.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.41.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.41.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.41.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.41.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.41.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.42.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.42.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.42.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.42.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.42.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.42.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.43.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.43.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.43.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.43.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.43.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.43.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.44.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.44.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.44.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.44.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.44.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.44.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.45.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.45.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.45.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.45.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.45.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.45.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.46.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.46.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.46.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.46.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.46.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.46.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.47.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.47.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.47.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.47.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.47.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.47.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.48.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.48.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.48.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.48.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.48.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.48.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.49.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.49.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.49.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.49.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.49.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.49.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.5.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.5.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.5.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.5.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.5.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.5.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.50.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.50.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.50.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.50.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.50.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.50.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.51.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.51.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.51.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.51.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.51.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.51.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.52.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.52.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.52.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.52.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.52.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.52.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.53.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.53.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.53.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.53.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.53.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.53.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.54.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.54.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.54.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.54.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.54.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.54.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.55.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.55.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.55.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.55.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.55.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.55.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.56.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.56.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.56.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.56.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.56.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.56.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.57.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.57.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.57.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.57.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.57.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.57.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.58.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.58.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.58.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.58.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.58.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.58.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.59.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.59.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.59.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.59.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.59.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.59.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.6.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.6.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.6.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.6.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.6.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.6.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.60.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.60.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.60.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.60.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.60.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.60.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.61.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.61.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.61.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.61.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.61.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.61.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.62.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.62.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.62.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.62.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.62.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.62.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.63.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.63.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.63.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.63.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.63.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.63.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.64.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.64.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.64.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.64.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.64.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.64.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.65.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.65.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.65.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.65.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.65.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.65.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.66.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.66.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.66.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.66.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.66.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.66.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.67.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.67.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.67.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.67.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.67.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.67.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.68.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.68.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.68.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.68.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.68.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.68.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.69.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.69.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.69.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.69.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.69.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.69.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.7.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.7.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.7.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.7.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.7.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.7.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.70.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.70.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.70.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.70.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.70.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.70.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.71.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.71.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.71.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.71.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.71.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.71.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.72.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.72.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.72.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.72.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.72.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.72.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.73.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.73.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.73.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.73.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.73.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.73.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.74.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.74.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.74.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.74.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.74.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.74.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.75.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.75.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.75.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.75.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.75.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.75.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.76.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.76.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.76.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.76.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.76.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.76.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.77.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.77.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.77.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.77.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.77.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.77.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.78.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.78.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.78.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.78.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.78.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.78.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.79.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.79.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.79.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.79.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.79.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.79.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.8.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.8.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.8.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.8.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.8.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.8.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.80.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.80.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.80.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.80.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.80.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.80.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.81.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.81.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.81.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.81.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.81.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.81.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.82.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.82.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.82.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.82.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.82.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.82.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.83.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.83.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.83.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.83.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.83.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.83.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.84.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.84.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.84.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.84.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.84.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.84.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.85.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.85.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.85.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.85.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.85.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.85.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.86.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.86.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.86.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.86.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.86.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.86.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.87.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.87.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.87.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.87.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.87.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.87.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.88.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.88.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.88.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.88.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.88.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.88.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.89.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.89.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.89.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.89.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.89.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.89.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.9.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.9.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.9.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.9.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.9.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.9.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.90.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.90.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.90.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.90.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.90.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.90.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.91.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.91.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.91.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.91.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.91.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.91.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.92.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.92.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.92.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.92.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.92.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.92.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.93.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.93.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.93.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.93.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.93.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.93.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.94.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.94.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.94.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.94.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.94.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.94.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.95.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.95.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.95.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.95.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.95.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.95.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.96.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.96.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.96.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.96.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.96.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.96.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.97.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.97.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.97.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.97.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.97.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.97.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.98.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.98.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.98.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.98.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.98.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.98.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.99.w1.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.99.w1.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.99.w2.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.99.w2.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.99.w3.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.99.w3.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.shared_experts.down_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.shared_experts.gate_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.shared_experts.up_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.input_layernorm.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.post_attention_layernorm.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.index_k_norm.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.index_k_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.index_q_norm.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.index_q_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.k_norm.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.k_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.k_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.o_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.o_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.q_norm.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.q_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.q_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.v_proj.weight": "model-00052-of-00059.safetensors", - "language_model.model.layers.52.self_attn.v_proj.weight_scale": "model-00052-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.e_score_correction_bias": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.gate.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.0.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.0.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.0.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.1.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.1.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.1.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.10.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.10.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.10.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.10.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.10.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.10.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.100.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.100.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.100.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.100.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.100.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.100.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.101.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.101.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.101.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.101.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.101.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.101.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.102.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.102.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.102.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.102.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.102.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.102.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.103.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.103.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.103.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.103.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.103.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.103.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.104.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.104.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.104.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.104.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.104.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.104.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.105.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.105.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.105.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.105.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.105.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.105.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.106.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.106.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.106.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.106.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.106.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.106.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.107.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.107.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.107.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.107.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.107.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.107.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.108.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.108.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.108.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.108.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.108.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.108.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.109.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.109.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.109.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.109.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.109.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.109.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.11.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.11.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.11.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.11.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.11.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.11.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.110.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.110.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.110.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.110.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.110.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.110.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.111.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.111.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.111.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.111.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.111.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.111.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.112.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.112.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.112.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.112.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.112.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.112.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.113.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.113.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.113.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.113.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.113.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.113.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.114.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.114.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.114.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.114.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.114.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.114.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.115.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.115.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.115.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.115.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.115.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.115.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.116.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.116.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.116.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.116.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.116.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.116.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.117.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.117.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.117.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.117.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.117.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.117.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.118.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.118.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.118.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.118.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.118.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.118.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.119.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.119.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.119.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.119.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.119.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.119.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.12.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.12.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.12.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.12.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.12.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.12.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.120.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.120.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.120.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.120.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.120.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.120.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.121.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.121.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.121.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.121.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.121.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.121.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.122.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.122.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.122.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.122.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.122.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.122.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.123.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.123.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.123.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.123.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.123.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.123.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.124.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.124.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.124.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.124.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.124.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.124.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.125.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.125.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.125.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.125.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.125.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.125.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.126.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.126.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.126.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.126.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.126.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.126.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.127.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.127.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.127.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.127.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.127.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.127.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.13.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.13.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.13.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.13.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.13.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.13.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.14.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.14.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.14.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.14.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.14.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.14.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.15.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.15.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.15.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.15.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.15.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.15.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.16.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.16.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.16.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.16.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.16.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.16.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.17.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.17.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.17.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.17.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.17.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.17.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.18.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.18.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.18.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.18.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.18.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.18.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.19.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.19.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.19.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.19.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.19.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.19.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.2.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.2.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.2.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.20.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.20.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.20.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.20.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.20.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.20.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.21.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.21.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.21.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.21.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.21.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.21.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.22.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.22.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.22.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.22.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.22.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.22.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.23.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.23.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.23.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.23.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.23.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.23.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.24.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.24.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.24.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.24.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.24.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.24.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.25.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.25.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.25.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.25.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.25.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.25.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.26.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.26.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.26.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.26.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.26.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.26.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.27.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.27.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.27.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.27.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.27.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.27.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.28.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.28.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.28.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.28.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.28.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.28.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.29.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.29.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.29.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.29.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.29.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.29.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.3.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.3.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.3.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.30.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.30.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.30.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.30.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.30.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.30.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.31.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.31.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.31.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.31.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.31.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.31.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.32.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.32.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.32.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.32.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.32.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.32.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.33.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.33.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.33.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.33.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.33.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.33.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.34.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.34.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.34.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.34.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.34.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.34.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.35.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.35.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.35.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.35.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.35.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.35.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.36.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.36.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.36.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.36.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.36.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.36.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.37.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.37.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.37.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.37.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.37.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.37.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.38.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.38.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.38.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.38.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.38.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.38.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.39.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.39.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.39.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.39.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.39.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.39.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.4.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.4.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.4.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.40.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.40.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.40.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.40.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.40.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.40.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.41.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.41.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.41.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.41.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.41.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.41.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.42.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.42.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.42.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.42.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.42.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.42.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.43.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.43.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.43.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.43.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.43.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.43.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.44.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.44.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.44.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.44.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.44.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.44.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.45.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.45.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.45.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.45.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.45.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.45.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.46.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.46.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.46.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.46.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.46.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.46.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.47.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.47.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.47.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.47.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.47.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.47.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.48.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.48.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.48.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.48.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.48.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.48.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.49.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.49.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.49.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.49.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.49.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.49.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.5.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.5.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.5.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.50.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.50.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.50.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.50.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.50.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.50.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.51.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.51.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.51.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.51.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.51.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.51.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.52.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.52.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.52.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.52.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.52.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.52.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.53.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.53.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.53.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.53.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.53.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.53.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.54.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.54.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.54.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.54.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.54.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.54.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.55.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.55.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.55.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.55.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.55.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.55.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.56.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.56.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.56.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.56.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.56.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.56.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.57.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.57.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.57.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.57.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.57.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.57.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.58.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.58.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.58.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.58.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.58.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.58.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.59.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.59.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.59.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.59.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.59.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.59.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.6.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.6.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.6.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.60.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.60.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.60.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.60.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.60.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.60.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.61.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.61.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.61.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.61.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.61.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.61.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.62.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.62.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.62.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.62.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.62.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.62.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.63.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.63.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.63.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.63.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.63.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.63.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.64.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.64.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.64.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.64.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.64.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.64.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.65.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.65.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.65.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.65.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.65.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.65.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.66.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.66.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.66.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.66.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.66.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.66.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.67.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.67.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.67.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.67.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.67.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.67.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.68.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.68.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.68.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.68.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.68.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.68.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.69.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.69.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.69.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.69.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.69.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.69.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.7.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.7.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.7.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.70.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.70.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.70.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.70.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.70.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.70.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.71.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.71.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.71.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.71.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.71.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.71.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.72.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.72.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.72.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.72.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.72.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.72.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.73.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.73.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.73.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.73.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.73.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.73.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.74.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.74.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.74.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.74.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.74.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.74.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.75.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.75.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.75.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.75.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.75.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.75.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.76.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.76.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.76.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.76.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.76.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.76.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.77.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.77.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.77.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.77.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.77.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.77.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.78.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.78.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.78.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.78.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.78.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.78.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.79.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.79.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.79.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.79.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.79.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.79.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.8.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.8.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.8.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.8.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.8.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.8.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.80.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.80.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.80.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.80.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.80.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.80.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.81.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.81.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.81.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.81.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.81.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.81.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.82.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.82.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.82.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.82.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.82.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.82.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.83.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.83.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.83.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.83.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.83.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.83.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.84.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.84.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.84.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.84.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.84.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.84.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.85.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.85.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.85.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.85.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.85.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.85.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.86.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.86.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.86.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.86.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.86.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.86.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.87.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.87.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.87.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.87.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.87.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.87.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.88.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.88.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.88.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.88.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.88.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.88.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.89.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.89.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.89.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.89.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.89.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.89.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.9.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.9.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.9.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.9.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.9.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.9.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.90.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.90.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.90.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.90.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.90.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.90.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.91.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.91.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.91.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.91.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.91.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.91.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.92.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.92.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.92.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.92.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.92.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.92.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.93.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.93.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.93.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.93.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.93.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.93.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.94.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.94.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.94.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.94.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.94.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.94.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.95.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.95.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.95.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.95.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.95.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.95.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.96.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.96.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.96.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.96.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.96.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.96.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.97.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.97.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.97.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.97.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.97.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.97.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.98.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.98.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.98.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.98.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.98.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.98.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.99.w1.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.99.w1.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.99.w2.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.99.w2.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.99.w3.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.experts.99.w3.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.shared_experts.down_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.shared_experts.gate_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.shared_experts.up_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.input_layernorm.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.post_attention_layernorm.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.index_k_norm.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.index_k_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.index_q_norm.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.index_q_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.k_norm.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.k_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.k_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.o_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.o_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.q_norm.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.q_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.q_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.v_proj.weight": "model-00033-of-00059.safetensors", - "language_model.model.layers.33.self_attn.v_proj.weight_scale": "model-00033-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.gate.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.108.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.108.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.108.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.108.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.108.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.108.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.109.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.109.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.109.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.109.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.109.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.109.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.11.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.11.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.11.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.11.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.11.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.11.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.110.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.110.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.110.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.110.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.110.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.110.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.111.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.111.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.111.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.111.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.111.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.111.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.112.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.112.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.112.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.112.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.112.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.112.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.113.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.113.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.113.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.113.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.113.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.113.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.114.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.114.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.114.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.114.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.114.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.114.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.115.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.115.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.115.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.115.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.115.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.115.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.116.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.116.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.116.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.116.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.116.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.116.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.117.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.117.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.117.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.117.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.117.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.117.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.118.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.118.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.118.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.118.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.118.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.118.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.119.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.119.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.119.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.119.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.119.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.119.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.12.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.12.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.12.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.12.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.12.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.12.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.120.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.120.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.120.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.120.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.120.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.120.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.121.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.121.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.121.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.121.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.121.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.121.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.122.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.122.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.122.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.122.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.122.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.122.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.123.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.123.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.123.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.123.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.123.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.123.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.124.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.124.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.124.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.124.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.124.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.124.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.125.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.125.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.125.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.125.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.125.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.125.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.126.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.126.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.126.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.126.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.126.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.126.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.127.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.127.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.127.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.127.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.127.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.127.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.13.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.13.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.13.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.13.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.13.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.13.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.14.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.14.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.14.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.14.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.14.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.14.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.15.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.15.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.15.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.15.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.15.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.15.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.16.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.16.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.16.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.16.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.16.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.16.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.17.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.17.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.17.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.17.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.17.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.17.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.18.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.18.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.18.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.18.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.18.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.18.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.19.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.19.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.19.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.19.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.19.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.19.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.2.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.2.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.2.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.2.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.2.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.2.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.20.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.20.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.20.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.20.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.20.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.20.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.21.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.21.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.21.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.21.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.21.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.21.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.22.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.22.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.22.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.22.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.22.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.22.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.23.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.23.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.23.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.23.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.23.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.23.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.24.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.24.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.24.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.24.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.24.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.24.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.25.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.25.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.25.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.25.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.25.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.25.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.26.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.26.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.26.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.26.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.26.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.26.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.27.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.27.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.27.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.27.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.27.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.27.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.28.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.28.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.28.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.28.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.28.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.28.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.29.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.29.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.29.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.29.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.29.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.29.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.3.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.3.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.3.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.3.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.3.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.3.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.30.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.30.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.30.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.30.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.30.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.30.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.31.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.31.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.31.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.31.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.31.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.31.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.32.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.32.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.32.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.32.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.32.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.32.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.33.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.33.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.33.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.33.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.33.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.33.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.34.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.34.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.34.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.34.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.34.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.34.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.35.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.35.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.35.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.35.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.35.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.35.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.36.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.36.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.36.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.36.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.36.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.36.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.37.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.37.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.37.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.37.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.37.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.37.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.38.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.38.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.38.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.38.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.38.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.38.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.39.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.39.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.39.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.39.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.39.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.39.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.4.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.4.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.4.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.4.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.4.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.4.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.40.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.40.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.40.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.40.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.40.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.40.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.41.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.41.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.41.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.41.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.41.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.41.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.42.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.42.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.42.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.42.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.42.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.42.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.43.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.43.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.43.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.43.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.43.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.43.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.44.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.44.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.44.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.44.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.44.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.44.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.45.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.45.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.45.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.45.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.45.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.45.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.46.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.46.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.46.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.46.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.46.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.46.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.47.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.47.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.47.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.47.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.47.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.47.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.48.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.48.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.48.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.48.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.48.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.48.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.49.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.49.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.49.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.49.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.49.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.49.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.5.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.5.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.5.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.5.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.5.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.5.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.50.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.50.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.50.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.50.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.50.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.50.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.51.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.51.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.51.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.51.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.51.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.51.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.52.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.52.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.52.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.52.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.52.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.52.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.53.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.53.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.53.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.53.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.53.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.53.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.54.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.54.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.54.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.54.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.54.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.54.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.55.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.55.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.55.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.55.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.55.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.55.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.56.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.56.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.56.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.56.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.56.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.56.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.57.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.57.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.57.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.57.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.57.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.57.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.58.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.58.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.58.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.58.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.58.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.58.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.59.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.59.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.59.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.59.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.59.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.59.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.6.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.6.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.6.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.6.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.6.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.6.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.60.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.60.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.60.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.60.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.60.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.60.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.61.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.61.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.61.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.61.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.61.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.61.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.62.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.62.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.62.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.62.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.62.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.62.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.63.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.63.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.63.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.63.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.63.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.63.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.64.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.64.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.64.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.64.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.64.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.64.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.65.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.65.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.65.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.65.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.65.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.65.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.66.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.66.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.66.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.66.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.66.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.66.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.67.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.67.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.67.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.67.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.67.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.67.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.68.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.68.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.68.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.68.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.68.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.68.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.69.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.69.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.69.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.69.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.69.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.69.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.7.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.7.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.7.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.7.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.7.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.7.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.70.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.70.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.70.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.70.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.70.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.70.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.71.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.71.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.71.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.71.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.71.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.71.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.72.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.72.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.72.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.72.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.72.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.72.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.73.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.73.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.73.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.73.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.73.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.73.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.74.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.74.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.74.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.74.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.74.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.74.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.75.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.75.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.75.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.75.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.75.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.75.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.76.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.76.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.76.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.76.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.76.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.76.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.77.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.77.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.77.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.77.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.77.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.77.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.78.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.78.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.78.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.78.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.78.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.78.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.79.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.79.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.79.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.79.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.79.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.79.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.8.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.8.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.8.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.8.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.8.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.8.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.80.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.80.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.80.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.80.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.80.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.80.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.81.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.81.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.81.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.81.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.81.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.81.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.82.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.82.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.82.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.82.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.82.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.82.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.83.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.83.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.83.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.83.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.83.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.83.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.84.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.84.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.84.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.84.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.84.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.84.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.85.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.85.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.85.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.85.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.85.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.85.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.86.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.86.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.86.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.86.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.86.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.86.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.87.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.87.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.87.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.87.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.87.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.87.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.88.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.88.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.88.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.88.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.88.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.88.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.89.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.89.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.89.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.89.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.89.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.89.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.9.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.9.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.9.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.9.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.9.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.9.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.90.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.90.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.90.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.90.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.90.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.90.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.91.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.91.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.91.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.91.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.91.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.91.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.92.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.92.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.92.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.92.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.92.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.92.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.93.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.93.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.93.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.93.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.93.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.93.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.94.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.94.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.94.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.94.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.94.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.94.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.95.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.95.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.95.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.95.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.95.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.95.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.96.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.96.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.96.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.96.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.96.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.96.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.97.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.97.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.97.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.97.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.97.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.97.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.98.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.98.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.98.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.98.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.98.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.98.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.99.w1.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.99.w1.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.99.w2.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.99.w2.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.99.w3.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.99.w3.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.shared_experts.down_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.shared_experts.gate_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.shared_experts.up_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.input_layernorm.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.post_attention_layernorm.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.index_k_norm.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.index_k_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.index_q_norm.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.index_q_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.k_norm.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.k_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.k_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.o_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.o_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.q_norm.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.q_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.q_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.v_proj.weight": "model-00056-of-00059.safetensors", - "language_model.model.layers.56.self_attn.v_proj.weight_scale": "model-00056-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.e_score_correction_bias": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.e_score_correction_bias": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.0.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.0.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.0.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.1.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.1.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.1.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.10.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.10.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.10.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.100.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.100.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.100.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.101.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.101.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.101.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.102.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.102.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.102.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.103.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.103.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.103.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.104.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.104.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.104.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.105.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.105.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.105.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.106.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.106.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.106.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.107.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.107.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.107.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.108.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.108.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.108.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.108.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.108.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.108.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.109.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.109.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.109.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.109.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.109.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.109.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.11.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.11.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.11.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.11.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.11.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.11.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.110.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.110.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.110.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.110.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.110.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.110.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.111.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.111.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.111.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.111.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.111.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.111.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.112.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.112.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.112.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.112.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.112.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.112.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.113.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.113.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.113.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.113.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.113.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.113.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.114.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.114.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.114.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.114.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.114.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.114.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.115.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.115.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.115.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.115.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.115.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.115.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.116.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.116.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.116.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.116.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.116.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.116.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.117.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.117.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.117.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.117.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.117.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.117.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.118.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.118.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.118.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.118.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.118.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.118.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.119.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.119.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.119.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.119.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.119.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.119.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.12.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.12.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.12.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.12.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.12.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.12.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.120.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.120.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.120.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.120.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.120.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.120.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.121.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.121.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.121.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.121.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.121.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.121.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.122.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.122.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.122.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.122.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.122.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.122.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.123.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.123.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.123.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.123.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.123.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.123.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.124.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.124.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.124.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.124.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.124.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.124.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.125.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.125.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.125.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.125.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.125.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.125.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.126.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.126.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.126.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.126.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.126.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.126.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.127.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.127.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.127.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.127.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.127.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.127.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.13.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.13.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.13.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.13.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.13.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.13.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.14.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.14.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.14.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.14.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.14.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.14.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.15.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.15.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.15.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.15.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.15.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.15.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.16.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.16.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.16.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.16.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.16.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.16.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.17.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.17.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.17.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.17.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.17.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.17.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.18.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.18.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.18.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.18.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.18.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.18.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.19.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.19.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.19.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.19.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.19.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.19.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.2.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.2.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.2.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.20.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.20.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.20.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.20.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.20.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.20.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.21.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.21.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.21.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.21.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.21.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.21.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.22.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.22.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.22.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.22.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.22.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.22.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.23.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.23.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.23.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.23.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.23.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.23.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.24.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.24.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.24.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.24.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.24.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.24.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.25.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.25.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.25.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.25.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.25.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.25.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.26.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.26.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.26.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.26.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.26.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.26.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.27.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.27.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.27.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.27.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.27.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.27.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.28.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.28.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.28.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.28.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.28.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.28.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.29.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.29.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.29.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.29.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.29.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.29.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.3.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.3.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.3.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.30.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.30.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.30.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.30.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.30.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.30.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.31.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.31.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.31.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.31.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.31.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.31.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.32.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.32.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.32.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.32.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.32.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.32.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.33.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.33.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.33.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.33.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.33.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.33.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.34.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.34.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.34.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.34.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.34.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.34.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.35.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.35.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.35.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.35.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.35.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.35.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.36.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.36.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.36.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.36.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.36.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.36.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.37.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.37.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.37.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.37.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.37.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.37.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.38.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.38.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.38.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.38.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.38.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.38.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.39.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.39.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.39.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.39.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.39.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.39.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.4.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.4.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.4.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.40.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.40.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.40.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.40.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.40.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.40.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.41.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.41.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.41.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.41.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.41.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.41.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.42.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.42.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.42.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.42.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.42.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.42.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.43.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.43.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.43.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.43.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.43.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.43.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.44.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.44.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.44.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.44.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.44.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.44.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.45.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.45.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.45.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.45.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.45.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.45.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.46.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.46.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.46.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.46.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.46.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.46.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.47.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.47.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.47.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.47.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.47.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.47.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.48.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.48.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.48.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.48.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.48.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.48.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.49.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.49.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.49.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.49.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.49.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.49.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.5.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.5.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.5.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.50.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.50.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.50.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.50.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.50.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.50.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.51.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.51.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.51.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.51.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.51.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.51.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.52.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.52.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.52.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.52.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.52.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.52.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.53.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.53.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.53.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.53.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.53.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.53.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.54.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.54.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.54.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.54.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.54.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.54.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.55.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.55.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.55.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.55.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.55.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.55.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.56.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.56.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.56.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.56.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.56.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.56.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.57.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.57.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.57.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.57.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.57.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.57.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.58.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.58.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.58.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.58.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.58.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.58.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.59.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.59.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.59.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.59.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.59.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.59.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.6.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.6.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.6.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.60.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.60.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.60.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.60.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.60.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.60.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.61.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.61.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.61.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.61.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.61.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.61.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.62.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.62.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.62.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.62.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.62.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.62.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.63.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.63.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.63.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.63.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.63.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.63.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.64.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.64.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.64.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.64.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.64.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.64.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.65.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.65.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.65.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.65.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.65.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.65.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.66.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.66.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.66.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.66.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.66.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.66.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.67.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.67.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.67.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.67.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.67.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.67.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.68.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.68.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.68.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.68.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.68.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.68.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.69.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.69.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.69.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.69.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.69.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.69.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.7.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.7.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.7.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.70.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.70.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.70.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.70.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.70.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.70.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.71.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.71.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.71.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.71.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.71.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.71.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.72.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.72.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.72.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.72.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.72.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.72.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.73.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.73.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.73.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.73.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.73.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.73.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.74.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.74.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.74.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.74.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.74.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.74.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.75.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.75.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.75.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.75.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.75.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.75.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.76.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.76.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.76.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.76.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.76.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.76.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.77.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.77.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.77.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.77.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.77.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.77.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.78.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.78.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.78.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.78.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.78.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.78.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.79.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.79.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.79.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.79.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.79.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.79.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.8.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.8.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.8.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.8.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.8.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.8.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.80.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.80.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.80.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.80.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.80.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.80.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.81.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.81.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.81.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.81.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.81.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.81.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.82.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.82.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.82.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.82.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.82.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.82.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.83.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.83.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.83.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.83.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.83.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.83.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.84.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.84.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.84.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.84.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.84.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.84.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.85.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.85.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.85.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.85.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.85.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.85.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.86.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.86.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.86.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.86.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.86.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.86.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.87.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.87.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.87.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.87.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.87.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.87.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.88.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.88.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.88.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.88.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.88.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.88.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.89.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.89.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.89.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.89.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.89.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.89.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.9.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.9.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.9.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.9.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.9.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.9.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.90.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.90.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.90.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.90.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.90.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.90.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.91.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.91.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.91.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.91.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.91.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.91.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.92.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.92.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.92.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.92.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.92.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.92.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.93.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.93.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.93.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.93.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.93.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.93.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.94.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.94.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.94.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.94.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.94.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.94.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.95.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.95.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.95.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.95.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.95.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.95.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.96.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.96.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.96.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.96.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.96.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.96.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.97.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.97.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.97.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.97.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.97.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.97.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.98.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.98.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.98.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.98.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.98.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.98.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.99.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.99.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.99.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.99.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.99.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.experts.99.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.shared_experts.down_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.shared_experts.gate_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.shared_experts.up_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.input_layernorm.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.post_attention_layernorm.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.index_k_norm.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.index_k_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.index_q_norm.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.index_q_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.k_norm.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.k_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.k_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.o_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.o_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.q_norm.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.q_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.q_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.v_proj.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.19.self_attn.v_proj.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.0.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.0.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.0.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.1.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.1.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.1.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.10.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.10.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.10.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.100.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.100.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.100.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.101.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.101.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.101.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.102.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.102.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.102.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.103.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.103.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.103.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.104.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.104.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.104.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.105.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.105.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.105.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.106.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.106.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.106.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.107.w1.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.107.w2.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.107.w3.weight_scale": "model-00019-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.gate.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.108.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.108.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.108.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.108.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.108.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.108.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.109.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.109.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.109.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.109.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.109.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.109.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.11.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.11.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.11.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.11.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.11.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.11.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.110.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.110.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.110.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.110.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.110.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.110.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.111.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.111.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.111.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.111.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.111.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.111.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.112.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.112.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.112.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.112.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.112.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.112.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.113.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.113.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.113.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.113.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.113.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.113.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.114.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.114.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.114.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.114.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.114.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.114.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.115.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.115.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.115.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.115.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.115.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.115.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.116.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.116.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.116.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.116.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.116.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.116.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.117.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.117.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.117.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.117.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.117.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.117.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.118.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.118.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.118.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.118.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.118.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.118.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.119.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.119.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.119.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.119.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.119.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.119.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.12.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.12.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.12.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.12.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.12.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.12.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.120.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.120.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.120.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.120.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.120.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.120.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.121.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.121.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.121.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.121.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.121.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.121.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.122.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.122.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.122.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.122.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.122.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.122.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.123.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.123.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.123.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.123.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.123.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.123.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.124.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.124.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.124.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.124.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.124.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.124.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.125.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.125.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.125.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.125.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.125.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.125.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.126.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.126.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.126.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.126.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.126.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.126.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.127.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.127.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.127.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.127.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.127.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.127.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.13.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.13.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.13.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.13.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.13.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.13.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.14.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.14.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.14.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.14.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.14.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.14.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.15.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.15.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.15.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.15.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.15.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.15.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.16.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.16.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.16.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.16.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.16.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.16.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.17.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.17.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.17.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.17.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.17.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.17.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.18.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.18.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.18.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.18.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.18.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.18.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.19.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.19.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.19.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.19.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.19.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.19.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.2.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.2.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.2.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.20.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.20.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.20.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.20.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.20.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.20.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.21.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.21.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.21.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.21.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.21.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.21.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.22.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.22.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.22.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.22.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.22.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.22.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.23.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.23.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.23.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.23.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.23.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.23.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.24.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.24.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.24.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.24.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.24.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.24.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.25.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.25.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.25.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.25.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.25.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.25.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.26.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.26.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.26.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.26.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.26.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.26.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.27.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.27.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.27.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.27.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.27.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.27.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.28.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.28.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.28.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.28.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.28.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.28.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.29.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.29.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.29.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.29.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.29.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.29.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.3.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.3.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.3.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.30.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.30.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.30.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.30.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.30.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.30.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.31.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.31.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.31.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.31.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.31.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.31.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.32.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.32.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.32.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.32.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.32.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.32.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.33.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.33.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.33.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.33.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.33.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.33.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.34.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.34.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.34.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.34.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.34.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.34.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.35.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.35.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.35.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.35.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.35.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.35.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.36.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.36.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.36.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.36.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.36.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.36.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.37.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.37.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.37.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.37.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.37.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.37.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.38.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.38.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.38.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.38.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.38.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.38.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.39.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.39.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.39.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.39.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.39.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.39.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.4.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.4.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.4.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.4.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.4.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.4.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.40.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.40.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.40.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.40.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.40.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.40.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.41.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.41.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.41.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.41.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.41.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.41.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.42.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.42.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.42.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.42.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.42.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.42.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.43.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.43.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.43.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.43.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.43.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.43.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.44.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.44.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.44.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.44.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.44.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.44.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.45.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.45.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.45.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.45.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.45.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.45.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.46.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.46.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.46.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.46.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.46.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.46.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.47.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.47.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.47.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.47.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.47.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.47.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.48.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.48.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.48.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.48.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.48.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.48.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.49.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.49.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.49.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.49.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.49.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.49.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.5.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.5.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.5.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.5.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.5.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.5.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.50.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.50.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.50.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.50.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.50.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.50.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.51.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.51.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.51.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.51.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.51.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.51.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.52.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.52.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.52.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.52.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.52.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.52.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.53.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.53.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.53.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.53.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.53.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.53.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.54.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.54.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.54.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.54.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.54.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.54.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.55.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.55.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.55.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.55.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.55.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.55.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.56.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.56.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.56.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.56.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.56.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.56.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.57.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.57.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.57.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.57.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.57.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.57.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.58.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.58.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.58.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.58.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.58.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.58.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.59.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.59.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.59.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.59.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.59.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.59.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.6.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.6.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.6.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.6.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.6.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.6.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.60.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.60.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.60.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.60.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.60.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.60.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.61.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.61.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.61.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.61.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.61.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.61.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.62.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.62.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.62.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.62.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.62.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.62.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.63.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.63.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.63.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.63.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.63.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.63.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.64.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.64.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.64.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.64.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.64.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.64.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.65.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.65.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.65.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.65.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.65.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.65.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.66.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.66.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.66.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.66.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.66.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.66.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.67.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.67.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.67.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.67.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.67.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.67.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.68.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.68.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.68.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.68.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.68.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.68.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.69.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.69.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.69.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.69.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.69.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.69.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.7.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.7.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.7.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.7.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.7.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.7.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.70.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.70.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.70.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.70.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.70.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.70.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.71.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.71.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.71.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.71.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.71.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.71.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.72.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.72.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.72.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.72.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.72.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.72.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.73.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.73.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.73.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.73.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.73.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.73.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.74.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.74.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.74.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.74.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.74.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.74.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.75.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.75.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.75.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.75.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.75.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.75.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.76.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.76.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.76.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.76.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.76.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.76.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.77.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.77.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.77.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.77.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.77.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.77.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.78.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.78.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.78.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.78.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.78.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.78.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.79.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.79.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.79.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.79.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.79.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.79.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.8.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.8.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.8.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.8.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.8.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.8.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.80.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.80.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.80.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.80.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.80.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.80.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.81.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.81.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.81.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.81.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.81.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.81.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.82.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.82.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.82.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.82.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.82.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.82.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.83.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.83.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.83.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.83.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.83.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.83.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.84.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.84.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.84.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.84.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.84.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.84.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.85.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.85.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.85.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.85.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.85.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.85.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.86.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.86.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.86.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.86.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.86.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.86.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.87.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.87.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.87.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.87.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.87.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.87.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.88.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.88.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.88.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.88.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.88.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.88.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.89.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.89.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.89.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.89.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.89.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.89.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.9.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.9.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.9.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.9.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.9.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.9.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.90.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.90.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.90.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.90.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.90.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.90.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.91.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.91.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.91.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.91.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.91.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.91.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.92.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.92.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.92.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.92.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.92.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.92.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.93.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.93.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.93.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.93.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.93.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.93.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.94.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.94.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.94.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.94.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.94.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.94.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.95.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.95.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.95.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.95.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.95.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.95.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.96.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.96.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.96.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.96.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.96.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.96.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.97.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.97.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.97.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.97.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.97.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.97.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.98.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.98.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.98.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.98.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.98.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.98.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.99.w1.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.99.w1.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.99.w2.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.99.w2.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.99.w3.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.99.w3.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.shared_experts.down_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.shared_experts.gate_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.shared_experts.up_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.input_layernorm.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.post_attention_layernorm.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.index_k_norm.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.index_k_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.index_q_norm.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.index_q_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.k_norm.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.k_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.k_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.o_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.o_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.q_norm.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.q_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.q_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.v_proj.weight": "model-00044-of-00059.safetensors", - "language_model.model.layers.44.self_attn.v_proj.weight_scale": "model-00044-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.e_score_correction_bias": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.e_score_correction_bias": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.0.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.0.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.0.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.1.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.1.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.1.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.10.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.10.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.10.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.100.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.100.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.100.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.101.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.101.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.101.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.102.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.102.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.102.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.103.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.103.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.103.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.104.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.104.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.104.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.105.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.105.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.105.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.106.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.106.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.106.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.107.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.107.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.107.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.108.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.108.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.108.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.108.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.108.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.108.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.109.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.109.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.109.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.109.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.109.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.109.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.11.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.11.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.11.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.110.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.110.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.110.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.110.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.110.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.110.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.111.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.111.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.111.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.111.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.111.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.111.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.112.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.112.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.112.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.112.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.112.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.112.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.113.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.113.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.113.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.113.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.113.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.113.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.114.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.114.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.114.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.114.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.114.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.114.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.115.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.115.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.115.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.115.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.115.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.115.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.116.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.116.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.116.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.116.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.116.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.116.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.117.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.117.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.117.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.117.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.117.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.117.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.118.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.118.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.118.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.118.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.118.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.118.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.119.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.119.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.119.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.119.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.119.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.119.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.12.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.12.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.12.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.120.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.120.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.120.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.120.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.120.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.120.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.121.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.121.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.121.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.121.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.121.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.121.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.122.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.122.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.122.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.122.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.122.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.122.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.123.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.123.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.123.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.123.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.123.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.123.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.124.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.124.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.124.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.124.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.124.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.124.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.125.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.125.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.125.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.125.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.125.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.125.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.126.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.126.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.126.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.126.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.126.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.126.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.127.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.127.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.127.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.127.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.127.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.127.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.13.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.13.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.13.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.14.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.14.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.14.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.15.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.15.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.15.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.16.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.16.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.16.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.17.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.17.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.17.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.18.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.18.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.18.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.19.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.19.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.19.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.2.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.2.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.2.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.20.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.20.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.20.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.21.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.21.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.21.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.22.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.22.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.22.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.23.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.23.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.23.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.24.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.24.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.24.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.25.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.25.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.25.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.26.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.26.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.26.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.27.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.27.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.27.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.28.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.28.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.28.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.29.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.29.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.29.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.3.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.3.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.3.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.30.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.30.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.30.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.31.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.31.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.31.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.32.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.32.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.32.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.32.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.32.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.32.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.33.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.33.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.33.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.33.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.33.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.33.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.34.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.34.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.34.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.34.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.34.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.34.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.35.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.35.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.35.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.35.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.35.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.35.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.36.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.36.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.36.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.36.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.36.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.36.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.37.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.37.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.37.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.37.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.37.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.37.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.38.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.38.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.38.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.38.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.38.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.38.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.39.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.39.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.39.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.39.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.39.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.39.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.4.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.4.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.4.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.40.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.40.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.40.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.40.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.40.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.40.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.41.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.41.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.41.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.41.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.41.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.41.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.42.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.42.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.42.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.42.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.42.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.42.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.43.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.43.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.43.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.43.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.43.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.43.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.44.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.44.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.44.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.44.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.44.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.44.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.45.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.45.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.45.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.45.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.45.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.45.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.46.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.46.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.46.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.46.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.46.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.46.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.47.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.47.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.47.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.47.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.47.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.47.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.48.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.48.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.48.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.48.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.48.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.48.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.49.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.49.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.49.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.49.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.49.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.49.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.5.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.5.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.5.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.50.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.50.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.50.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.50.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.50.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.50.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.51.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.51.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.51.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.51.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.51.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.51.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.52.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.52.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.52.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.52.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.52.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.52.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.53.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.53.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.53.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.53.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.53.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.53.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.54.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.54.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.54.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.54.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.54.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.54.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.55.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.55.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.55.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.55.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.55.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.55.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.56.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.56.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.56.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.56.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.56.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.56.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.57.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.57.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.57.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.57.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.57.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.57.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.58.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.58.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.58.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.58.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.58.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.58.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.59.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.59.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.59.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.59.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.59.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.59.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.6.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.6.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.6.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.60.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.60.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.60.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.60.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.60.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.60.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.61.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.61.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.61.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.61.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.61.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.61.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.62.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.62.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.62.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.62.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.62.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.62.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.63.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.63.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.63.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.63.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.63.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.63.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.64.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.64.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.64.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.64.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.64.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.64.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.65.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.65.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.65.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.65.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.65.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.65.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.66.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.66.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.66.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.66.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.66.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.66.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.67.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.67.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.67.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.67.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.67.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.67.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.68.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.68.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.68.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.68.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.68.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.68.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.69.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.69.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.69.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.69.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.69.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.69.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.7.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.7.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.7.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.70.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.70.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.70.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.70.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.70.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.70.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.71.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.71.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.71.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.71.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.71.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.71.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.72.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.72.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.72.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.72.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.72.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.72.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.73.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.73.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.73.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.73.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.73.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.73.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.74.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.74.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.74.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.74.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.74.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.74.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.75.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.75.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.75.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.75.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.75.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.75.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.76.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.76.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.76.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.76.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.76.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.76.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.77.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.77.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.77.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.77.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.77.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.77.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.78.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.78.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.78.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.78.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.78.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.78.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.79.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.79.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.79.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.79.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.79.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.79.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.8.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.8.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.8.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.80.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.80.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.80.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.80.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.80.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.80.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.81.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.81.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.81.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.81.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.81.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.81.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.82.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.82.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.82.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.82.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.82.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.82.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.83.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.83.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.83.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.83.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.83.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.83.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.84.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.84.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.84.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.84.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.84.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.84.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.85.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.85.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.85.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.85.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.85.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.85.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.86.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.86.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.86.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.86.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.86.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.86.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.87.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.87.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.87.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.87.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.87.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.87.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.88.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.88.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.88.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.88.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.88.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.88.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.89.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.89.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.89.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.89.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.89.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.89.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.9.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.9.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.9.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.90.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.90.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.90.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.90.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.90.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.90.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.91.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.91.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.91.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.91.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.91.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.91.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.92.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.92.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.92.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.92.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.93.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.93.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.93.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.94.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.94.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.94.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.95.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.95.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.95.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.96.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.96.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.96.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.97.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.97.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.97.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.98.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.98.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.98.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.99.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.99.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.experts.99.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.shared_experts.down_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.shared_experts.gate_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.shared_experts.up_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.input_layernorm.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.post_attention_layernorm.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.index_k_norm.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.index_k_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.index_q_norm.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.index_q_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.k_norm.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.k_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.o_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.q_norm.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.q_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.v_proj.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.0.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.0.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.0.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.1.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.1.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.1.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.10.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.10.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.10.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.100.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.100.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.100.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.101.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.101.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.101.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.102.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.102.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.102.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.103.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.103.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.103.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.104.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.104.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.104.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.105.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.105.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.105.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.106.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.106.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.106.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.107.w1.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.107.w2.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00059.safetensors", - "language_model.model.layers.44.block_sparse_moe.experts.107.w3.weight_scale": "model-00010-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.6.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.60.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.60.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.60.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.60.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.60.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.60.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.61.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.61.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.61.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.61.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.61.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.61.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.62.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.62.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.62.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.62.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.62.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.62.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.63.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.63.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.63.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.63.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.63.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.63.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.64.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.64.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.64.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.64.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.64.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.64.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.65.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.65.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.65.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.65.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.65.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.65.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.66.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.66.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.66.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.66.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.66.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.66.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.67.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.67.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.67.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.67.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.67.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.67.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.68.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.68.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.68.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.68.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.68.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.68.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.69.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.69.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.69.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.69.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.69.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.69.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.7.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.7.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.7.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.70.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.70.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.70.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.70.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.70.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.70.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.71.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.71.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.71.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.71.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.71.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.71.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.72.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.72.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.72.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.72.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.72.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.72.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.73.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.73.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.73.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.73.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.73.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.73.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.74.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.74.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.74.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.74.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.74.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.74.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.75.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.75.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.75.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.75.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.75.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.75.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.76.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.76.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.76.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.76.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.76.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.76.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.77.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.77.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.77.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.77.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.77.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.77.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.78.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.78.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.78.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.78.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.78.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.78.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.79.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.79.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.79.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.79.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.79.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.79.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.8.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.8.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.8.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.8.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.8.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.8.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.80.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.80.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.80.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.80.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.80.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.80.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.81.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.81.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.81.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.81.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.81.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.81.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.82.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.82.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.82.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.82.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.82.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.82.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.83.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.83.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.83.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.83.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.83.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.83.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.84.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.84.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.84.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.84.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.84.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.84.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.85.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.85.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.85.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.85.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.85.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.85.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.86.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.86.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.86.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.86.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.86.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.86.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.87.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.87.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.87.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.87.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.87.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.87.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.88.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.88.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.88.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.88.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.88.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.88.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.89.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.89.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.89.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.89.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.89.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.89.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.9.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.9.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.9.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.9.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.9.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.9.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.90.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.90.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.90.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.90.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.90.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.90.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.91.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.91.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.91.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.91.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.91.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.91.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.92.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.92.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.92.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.92.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.92.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.92.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.93.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.93.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.93.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.93.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.93.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.93.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.94.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.94.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.94.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.94.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.94.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.94.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.95.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.95.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.95.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.95.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.95.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.95.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.96.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.96.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.96.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.96.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.96.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.96.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.97.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.97.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.97.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.97.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.97.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.97.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.98.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.98.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.98.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.98.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.98.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.98.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.99.w1.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.99.w1.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.99.w2.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.99.w2.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.99.w3.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.99.w3.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.shared_experts.down_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.shared_experts.gate_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.shared_experts.up_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.input_layernorm.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.post_attention_layernorm.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.index_k_norm.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.index_k_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.index_q_norm.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.index_q_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.k_norm.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.k_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.k_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.o_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.o_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.q_norm.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.q_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.q_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.v_proj.weight": "model-00025-of-00059.safetensors", - "language_model.model.layers.25.self_attn.v_proj.weight_scale": "model-00025-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.e_score_correction_bias": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.gate.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.e_score_correction_bias": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.0.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.0.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.0.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.1.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.1.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.1.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.10.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.10.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.10.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.100.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.100.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.100.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.101.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.101.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.101.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.102.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.102.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.102.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.103.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.103.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.103.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.104.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.104.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.104.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.105.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.105.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.105.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.106.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.106.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.106.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.107.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.107.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.107.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.108.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.108.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.108.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.108.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.108.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.108.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.109.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.109.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.109.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.109.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.109.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.109.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.11.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.11.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.11.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.110.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.110.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.110.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.110.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.110.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.110.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.111.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.111.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.111.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.111.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.111.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.111.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.112.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.112.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.112.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.112.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.112.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.112.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.113.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.113.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.113.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.113.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.113.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.113.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.114.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.114.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.114.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.114.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.114.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.114.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.115.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.115.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.115.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.115.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.115.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.115.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.116.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.116.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.116.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.116.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.116.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.116.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.117.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.117.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.117.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.117.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.117.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.117.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.118.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.118.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.118.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.118.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.118.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.118.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.119.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.119.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.119.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.119.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.119.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.119.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.12.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.12.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.12.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.120.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.120.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.120.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.120.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.120.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.120.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.121.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.121.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.121.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.121.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.121.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.121.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.122.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.122.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.122.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.122.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.122.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.122.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.123.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.123.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.123.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.123.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.123.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.123.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.124.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.124.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.124.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.124.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.124.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.124.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.125.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.125.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.125.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.125.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.125.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.125.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.126.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.126.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.126.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.126.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.126.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.126.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.127.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.127.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.127.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.127.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.127.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.127.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.13.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.13.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.13.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.14.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.14.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.14.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.15.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.15.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.15.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.16.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.16.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.16.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.17.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.17.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.17.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.18.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.18.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.18.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.19.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.19.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.19.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.2.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.2.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.2.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.20.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.20.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.20.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.21.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.21.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.21.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.22.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.22.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.22.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.23.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.23.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.23.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.24.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.24.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.24.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.25.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.25.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.25.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.26.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.26.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.26.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.27.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.27.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.27.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.28.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.28.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.28.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.29.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.29.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.29.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.3.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.3.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.3.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.30.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.30.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.30.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.31.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.31.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.31.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.32.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.32.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.32.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.32.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.32.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.32.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.33.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.33.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.33.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.33.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.33.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.33.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.34.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.34.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.34.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.34.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.34.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.34.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.35.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.35.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.35.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.35.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.35.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.35.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.36.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.36.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.36.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.36.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.36.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.36.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.37.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.37.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.37.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.37.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.37.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.37.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.38.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.38.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.38.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.38.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.38.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.38.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.39.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.39.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.39.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.39.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.39.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.39.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.4.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.4.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.4.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.40.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.40.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.40.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.40.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.40.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.40.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.41.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.41.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.41.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.41.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.41.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.41.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.42.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.42.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.42.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.42.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.42.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.42.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.43.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.43.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.43.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.43.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.43.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.43.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.44.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.44.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.44.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.44.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.44.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.44.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.45.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.45.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.45.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.45.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.45.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.45.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.46.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.46.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.46.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.46.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.46.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.46.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.47.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.47.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.47.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.47.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.47.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.47.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.48.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.48.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.48.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.48.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.48.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.48.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.49.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.49.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.49.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.49.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.49.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.49.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.5.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.5.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.5.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.50.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.50.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.50.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.50.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.50.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.50.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.51.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.51.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.51.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.51.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.51.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.51.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.52.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.52.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.52.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.52.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.52.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.52.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.53.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.53.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.53.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.53.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.53.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.53.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.54.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.54.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.54.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.54.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.54.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.54.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.55.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.55.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.55.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.55.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.55.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.55.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.56.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.56.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.56.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.56.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.56.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.56.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.57.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.57.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.57.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.57.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.57.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.57.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.58.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.58.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.58.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.58.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.58.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.58.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.59.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.59.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.59.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.59.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.59.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.59.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.6.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.6.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.6.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.60.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.60.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.60.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.60.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.60.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.60.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.61.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.61.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.61.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.61.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.61.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.61.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.62.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.62.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.62.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.62.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.62.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.62.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.63.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.63.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.63.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.64.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.64.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.64.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.64.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.65.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.65.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.65.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.65.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.65.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.65.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.66.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.66.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.66.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.66.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.66.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.66.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.67.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.67.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.67.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.67.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.67.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.67.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.68.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.68.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.68.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.68.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.68.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.68.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.69.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.69.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.69.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.69.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.69.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.69.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.7.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.7.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.7.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.70.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.70.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.70.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.70.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.70.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.70.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.71.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.71.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.71.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.71.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.71.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.71.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.72.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.72.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.72.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.72.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.72.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.72.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.73.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.73.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.73.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.73.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.73.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.73.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.74.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.74.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.74.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.74.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.74.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.74.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.75.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.75.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.75.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.75.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.75.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.75.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.76.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.76.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.76.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.76.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.76.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.76.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.77.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.77.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.77.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.77.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.77.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.77.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.78.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.78.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.78.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.78.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.78.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.78.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.79.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.79.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.79.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.79.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.79.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.79.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.8.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.8.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.8.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.80.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.80.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.80.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.80.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.80.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.80.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.81.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.81.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.81.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.81.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.81.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.81.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.82.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.82.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.82.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.82.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.82.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.82.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.83.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.83.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.83.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.83.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.83.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.83.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.84.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.84.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.84.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.84.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.84.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.84.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.85.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.85.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.85.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.85.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.85.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.85.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.86.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.86.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.86.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.86.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.86.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.86.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.87.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.87.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.87.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.87.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.87.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.87.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.88.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.88.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.88.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.88.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.88.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.88.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.89.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.89.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.89.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.89.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.89.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.89.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.9.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.9.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.9.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.90.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.90.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.90.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.90.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.90.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.90.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.91.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.91.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.91.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.91.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.91.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.91.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.92.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.92.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.92.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.92.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.92.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.92.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.93.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.93.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.93.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.93.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.93.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.93.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.94.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.94.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.94.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.94.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.94.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.94.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.95.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.95.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.95.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.95.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.95.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.95.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.96.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.96.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.96.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.96.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.96.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.96.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.97.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.97.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.97.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.97.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.97.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.97.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.98.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.98.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.98.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.98.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.98.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.98.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.99.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.99.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.99.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.99.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.99.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.experts.99.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.shared_experts.down_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.shared_experts.gate_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.shared_experts.up_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.input_layernorm.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.post_attention_layernorm.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.index_k_norm.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.index_k_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.index_q_norm.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.index_q_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.k_norm.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.k_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.k_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.o_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.o_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.q_norm.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.q_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.q_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.v_proj.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.14.self_attn.v_proj.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.0.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.0.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.0.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.1.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.1.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.1.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.10.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.10.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.10.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.100.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.100.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.100.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.101.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.101.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.101.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.102.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.102.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.102.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.103.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.103.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.103.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.104.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.104.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.104.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.105.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.105.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.105.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.106.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.106.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.106.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.107.w1.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.107.w2.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00059.safetensors", - "language_model.model.layers.48.block_sparse_moe.experts.107.w3.weight_scale": "model-00014-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.gate.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.108.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.108.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.108.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.108.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.108.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.108.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.109.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.109.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.109.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.109.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.109.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.109.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.11.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.11.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.11.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.11.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.11.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.11.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.110.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.110.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.110.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.110.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.110.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.110.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.111.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.111.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.111.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.111.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.111.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.111.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.112.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.112.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.112.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.112.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.112.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.112.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.113.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.113.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.113.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.113.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.113.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.113.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.114.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.114.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.114.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.114.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.114.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.114.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.115.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.115.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.115.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.115.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.115.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.115.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.116.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.116.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.116.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.116.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.116.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.116.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.117.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.117.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.117.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.117.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.117.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.117.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.118.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.118.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.118.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.118.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.118.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.118.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.119.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.119.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.119.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.119.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.119.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.119.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.12.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.12.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.12.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.12.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.12.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.12.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.120.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.120.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.120.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.120.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.120.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.120.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.121.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.121.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.121.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.121.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.121.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.121.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.122.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.122.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.122.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.122.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.122.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.122.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.123.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.123.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.123.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.123.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.123.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.123.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.124.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.124.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.124.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.124.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.124.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.124.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.125.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.125.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.125.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.125.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.125.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.125.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.126.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.126.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.126.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.126.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.126.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.126.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.127.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.127.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.127.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.127.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.127.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.127.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.13.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.13.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.13.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.13.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.13.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.13.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.14.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.14.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.14.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.14.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.14.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.14.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.15.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.15.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.15.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.15.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.15.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.15.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.16.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.16.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.16.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.16.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.16.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.16.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.17.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.17.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.17.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.17.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.17.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.17.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.18.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.18.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.18.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.18.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.18.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.18.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.19.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.19.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.19.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.19.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.19.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.19.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.2.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.2.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.2.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.20.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.20.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.20.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.20.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.20.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.20.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.21.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.21.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.21.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.21.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.21.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.21.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.22.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.22.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.22.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.22.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.22.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.22.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.23.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.23.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.23.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.23.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.23.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.23.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.24.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.24.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.24.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.24.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.24.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.24.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.25.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.25.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.25.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.25.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.25.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.25.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.26.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.26.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.26.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.26.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.26.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.26.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.27.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.27.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.27.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.27.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.27.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.27.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.28.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.28.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.28.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.28.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.28.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.28.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.29.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.29.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.29.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.29.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.29.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.29.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.3.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.3.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.3.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.3.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.3.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.3.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.30.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.30.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.30.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.30.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.30.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.30.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.31.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.31.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.31.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.31.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.31.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.31.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.32.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.32.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.32.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.32.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.32.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.32.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.33.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.33.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.33.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.33.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.33.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.33.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.34.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.34.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.34.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.34.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.34.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.34.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.35.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.35.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.35.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.35.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.35.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.35.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.36.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.36.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.36.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.36.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.36.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.36.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.37.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.37.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.37.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.37.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.37.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.37.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.38.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.38.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.38.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.38.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.38.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.38.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.39.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.39.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.39.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.39.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.39.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.39.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.4.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.4.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.4.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.4.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.4.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.4.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.40.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.40.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.40.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.40.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.40.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.40.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.41.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.41.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.41.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.41.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.41.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.41.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.42.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.42.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.42.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.42.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.42.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.42.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.43.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.43.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.43.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.43.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.43.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.43.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.44.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.44.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.44.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.44.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.44.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.44.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.45.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.45.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.45.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.45.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.45.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.45.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.46.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.46.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.46.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.46.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.46.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.46.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.47.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.47.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.47.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.47.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.47.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.47.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.48.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.48.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.48.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.48.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.48.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.48.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.49.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.49.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.49.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.49.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.49.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.49.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.5.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.5.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.5.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.5.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.5.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.5.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.50.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.50.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.50.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.50.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.50.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.50.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.51.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.51.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.51.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.51.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.51.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.51.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.52.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.52.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.52.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.52.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.52.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.52.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.53.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.53.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.53.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.53.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.53.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.53.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.54.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.54.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.54.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.54.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.54.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.54.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.55.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.55.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.55.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.55.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.55.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.55.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.56.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.56.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.56.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.56.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.56.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.56.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.57.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.57.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.57.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.57.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.57.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.57.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.58.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.58.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.58.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.58.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.58.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.58.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.59.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.59.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.59.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.59.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.59.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.59.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.6.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.6.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.6.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.6.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.6.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.6.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.60.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.60.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.60.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.60.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.60.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.60.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.61.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.61.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.61.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.61.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.61.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.61.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.62.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.62.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.62.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.62.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.62.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.62.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.63.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.63.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.63.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.63.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.63.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.63.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.64.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.64.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.64.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.64.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.64.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.64.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.65.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.65.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.65.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.65.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.65.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.65.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.66.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.66.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.66.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.66.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.66.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.66.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.67.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.67.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.67.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.67.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.67.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.67.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.68.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.68.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.68.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.68.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.68.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.68.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.69.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.69.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.69.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.69.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.69.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.69.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.7.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.7.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.7.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.7.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.7.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.7.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.70.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.70.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.70.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.70.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.70.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.70.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.71.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.71.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.71.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.71.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.71.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.71.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.72.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.72.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.72.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.72.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.72.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.72.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.73.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.73.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.73.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.73.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.73.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.73.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.74.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.74.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.74.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.74.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.74.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.74.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.75.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.75.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.75.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.75.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.75.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.75.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.76.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.76.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.76.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.76.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.76.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.76.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.77.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.77.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.77.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.77.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.77.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.77.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.78.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.78.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.78.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.78.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.78.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.78.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.79.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.79.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.79.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.79.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.79.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.79.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.8.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.8.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.8.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.8.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.8.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.8.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.80.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.80.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.80.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.80.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.80.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.80.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.81.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.81.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.81.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.81.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.81.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.81.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.82.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.82.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.82.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.82.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.82.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.82.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.83.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.83.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.83.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.83.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.83.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.83.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.84.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.84.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.84.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.84.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.84.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.84.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.85.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.85.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.85.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.85.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.85.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.85.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.86.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.86.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.86.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.86.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.86.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.86.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.87.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.87.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.87.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.87.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.87.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.87.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.88.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.88.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.88.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.88.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.88.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.88.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.89.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.89.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.89.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.89.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.89.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.89.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.9.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.9.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.9.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.9.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.9.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.9.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.90.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.90.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.90.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.90.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.90.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.90.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.91.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.91.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.91.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.91.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.91.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.91.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.92.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.92.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.92.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.92.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.92.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.92.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.93.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.93.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.93.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.93.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.93.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.93.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.94.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.94.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.94.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.94.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.94.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.94.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.95.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.95.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.95.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.95.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.95.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.95.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.96.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.96.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.96.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.96.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.96.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.96.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.97.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.97.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.97.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.97.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.97.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.97.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.98.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.98.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.98.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.98.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.98.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.98.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.99.w1.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.99.w1.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.99.w2.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.99.w2.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.99.w3.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.experts.99.w3.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.shared_experts.down_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.shared_experts.gate_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.shared_experts.up_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.input_layernorm.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.post_attention_layernorm.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.index_k_norm.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.index_k_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.index_q_norm.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.index_q_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.k_norm.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.k_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.k_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.o_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.o_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.q_norm.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.q_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.q_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.v_proj.weight": "model-00051-of-00059.safetensors", - "language_model.model.layers.51.self_attn.v_proj.weight_scale": "model-00051-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.e_score_correction_bias": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.gate.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.e_score_correction_bias": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.0.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.0.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.0.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.1.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.1.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.1.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.10.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.10.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.10.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.10.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.10.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.10.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.100.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.100.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.100.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.100.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.100.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.100.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.101.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.101.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.101.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.101.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.101.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.101.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.102.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.102.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.102.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.102.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.102.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.102.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.103.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.103.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.103.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.103.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.103.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.103.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.104.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.104.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.104.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.104.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.104.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.104.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.105.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.105.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.105.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.105.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.105.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.105.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.106.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.106.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.106.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.106.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.106.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.106.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.107.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.107.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.107.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.107.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.107.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.107.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.108.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.108.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.108.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.108.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.108.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.108.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.109.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.109.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.109.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.109.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.109.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.109.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.11.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.11.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.11.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.11.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.11.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.11.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.110.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.110.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.110.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.110.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.110.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.110.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.111.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.111.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.111.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.111.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.111.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.111.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.112.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.112.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.112.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.112.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.112.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.112.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.113.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.113.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.113.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.113.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.113.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.113.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.114.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.114.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.114.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.114.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.114.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.114.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.115.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.115.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.115.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.115.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.115.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.115.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.116.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.116.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.116.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.116.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.116.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.116.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.117.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.117.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.117.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.117.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.117.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.117.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.118.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.118.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.118.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.118.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.118.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.118.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.119.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.119.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.119.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.119.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.119.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.119.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.12.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.12.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.12.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.12.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.12.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.12.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.120.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.120.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.120.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.120.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.120.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.120.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.121.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.121.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.121.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.121.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.121.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.121.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.122.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.122.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.122.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.122.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.122.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.122.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.123.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.123.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.123.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.123.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.123.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.123.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.124.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.124.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.124.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.124.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.124.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.124.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.125.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.125.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.125.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.125.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.125.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.125.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.126.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.126.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.126.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.126.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.126.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.126.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.127.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.127.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.127.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.127.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.127.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.127.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.13.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.13.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.13.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.13.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.13.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.13.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.14.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.14.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.14.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.14.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.14.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.14.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.15.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.15.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.15.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.15.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.15.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.15.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.16.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.16.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.16.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.16.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.16.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.16.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.17.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.17.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.17.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.17.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.17.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.17.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.18.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.18.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.18.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.18.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.18.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.18.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.19.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.19.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.19.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.19.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.19.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.19.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.2.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.2.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.2.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.20.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.20.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.20.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.20.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.20.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.20.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.21.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.21.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.21.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.21.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.21.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.21.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.22.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.22.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.22.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.22.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.22.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.22.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.23.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.23.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.23.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.23.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.23.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.23.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.24.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.24.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.24.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.24.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.24.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.24.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.25.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.25.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.25.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.25.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.25.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.25.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.26.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.26.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.26.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.26.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.26.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.26.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.27.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.27.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.27.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.27.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.27.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.27.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.28.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.28.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.28.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.28.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.28.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.28.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.29.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.29.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.29.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.29.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.29.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.29.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.3.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.3.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.3.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.30.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.30.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.30.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.30.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.30.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.30.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.31.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.31.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.31.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.31.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.31.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.31.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.32.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.32.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.32.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.32.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.32.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.32.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.33.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.33.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.33.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.33.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.33.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.33.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.34.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.34.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.34.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.34.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.34.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.34.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.35.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.35.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.35.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.35.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.35.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.35.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.36.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.36.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.36.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.36.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.36.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.36.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.37.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.37.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.37.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.37.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.37.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.37.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.38.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.38.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.38.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.38.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.38.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.38.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.39.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.39.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.39.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.39.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.39.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.39.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.4.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.4.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.4.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.40.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.40.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.40.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.40.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.40.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.40.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.41.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.41.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.41.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.41.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.41.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.41.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.42.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.42.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.42.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.42.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.42.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.42.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.43.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.43.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.43.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.43.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.43.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.43.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.44.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.44.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.44.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.44.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.44.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.44.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.45.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.45.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.45.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.45.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.45.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.45.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.46.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.46.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.46.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.46.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.46.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.46.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.47.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.47.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.47.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.47.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.47.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.47.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.48.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.48.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.48.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.48.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.48.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.48.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.49.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.49.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.49.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.49.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.49.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.49.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.5.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.5.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.5.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.50.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.50.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.50.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.50.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.50.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.50.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.51.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.51.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.51.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.51.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.51.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.51.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.52.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.52.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.52.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.52.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.52.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.52.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.53.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.53.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.53.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.53.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.53.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.53.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.54.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.54.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.54.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.54.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.54.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.54.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.55.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.55.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.55.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.55.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.55.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.55.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.56.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.56.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.56.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.56.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.56.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.56.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.57.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.57.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.57.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.57.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.57.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.57.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.58.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.58.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.58.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.58.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.58.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.58.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.59.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.59.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.59.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.59.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.59.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.59.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.6.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.6.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.6.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.60.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.60.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.60.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.60.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.60.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.60.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.61.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.61.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.61.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.61.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.61.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.61.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.62.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.62.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.62.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.62.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.62.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.62.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.63.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.63.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.63.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.63.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.63.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.63.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.64.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.64.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.64.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.64.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.64.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.64.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.65.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.65.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.65.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.65.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.65.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.65.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.66.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.66.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.66.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.66.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.66.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.66.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.67.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.67.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.67.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.67.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.67.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.67.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.68.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.68.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.68.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.68.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.68.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.68.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.69.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.69.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.69.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.69.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.69.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.69.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.7.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.7.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.7.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.70.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.70.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.70.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.70.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.70.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.70.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.71.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.71.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.71.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.71.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.71.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.71.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.72.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.72.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.72.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.72.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.72.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.72.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.73.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.73.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.73.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.73.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.73.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.73.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.74.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.74.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.74.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.74.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.74.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.74.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.75.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.75.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.75.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.75.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.75.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.75.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.76.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.76.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.76.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.76.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.76.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.76.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.77.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.77.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.77.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.77.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.77.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.77.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.78.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.78.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.78.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.78.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.78.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.78.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.79.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.79.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.79.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.79.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.79.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.79.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.8.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.8.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.8.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.8.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.8.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.8.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.80.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.80.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.80.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.80.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.80.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.80.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.81.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.81.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.81.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.81.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.81.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.81.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.82.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.82.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.82.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.82.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.82.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.82.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.83.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.83.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.83.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.83.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.83.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.83.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.84.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.84.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.84.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.84.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.84.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.84.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.85.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.85.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.85.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.85.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.85.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.85.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.86.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.86.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.86.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.86.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.86.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.86.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.87.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.87.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.87.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.87.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.87.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.87.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.88.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.88.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.88.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.88.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.88.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.88.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.89.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.89.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.89.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.89.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.89.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.89.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.9.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.9.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.9.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.9.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.9.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.9.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.90.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.90.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.90.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.90.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.90.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.90.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.91.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.91.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.91.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.91.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.91.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.91.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.92.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.92.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.92.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.92.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.92.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.92.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.93.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.93.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.93.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.93.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.93.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.93.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.94.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.94.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.94.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.94.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.94.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.94.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.95.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.95.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.95.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.95.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.95.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.95.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.96.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.96.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.96.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.96.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.96.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.96.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.97.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.97.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.97.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.97.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.97.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.97.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.98.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.98.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.98.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.98.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.98.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.98.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.99.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.99.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.99.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.99.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.99.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.experts.99.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.shared_experts.down_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.shared_experts.gate_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.shared_experts.up_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.input_layernorm.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.post_attention_layernorm.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.index_k_norm.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.index_k_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.index_q_norm.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.index_q_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.k_norm.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.k_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.k_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.o_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.o_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.q_norm.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.q_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.q_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.v_proj.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.22.self_attn.v_proj.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.0.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.0.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.0.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.1.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.1.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.1.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.10.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.10.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.10.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.10.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.10.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.10.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.100.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.100.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.100.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.100.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.100.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.100.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.101.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.101.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.101.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.101.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.101.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.101.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.102.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.102.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.102.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.102.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.102.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.102.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.103.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.103.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.103.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.103.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.103.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.103.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.104.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.104.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.104.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.104.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.104.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.104.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.105.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.105.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.105.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.105.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.105.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.105.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.106.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.106.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.106.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.106.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.106.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.106.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.107.w1.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.107.w1.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.107.w2.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.107.w2.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.107.w3.weight": "model-00022-of-00059.safetensors", - "language_model.model.layers.56.block_sparse_moe.experts.107.w3.weight_scale": "model-00022-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.e_score_correction_bias": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.gate.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.e_score_correction_bias": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.0.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.0.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.0.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.1.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.1.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.1.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.10.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.10.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.10.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.100.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.100.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.100.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.101.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.101.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.101.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.102.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.102.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.102.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.103.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.103.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.103.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.104.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.104.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.104.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.105.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.105.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.105.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.106.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.106.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.106.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.107.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.107.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.107.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.108.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.108.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.108.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.109.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.109.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.109.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.11.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.11.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.11.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.110.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.110.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.110.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.111.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.111.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.111.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.112.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.112.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.112.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.112.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.112.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.112.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.113.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.113.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.113.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.113.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.113.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.113.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.114.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.114.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.114.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.114.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.114.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.114.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.115.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.115.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.115.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.115.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.115.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.115.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.116.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.116.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.116.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.116.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.116.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.116.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.117.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.117.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.117.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.117.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.117.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.117.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.118.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.118.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.118.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.118.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.118.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.118.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.119.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.119.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.119.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.119.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.119.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.119.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.12.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.12.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.12.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.120.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.120.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.120.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.120.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.120.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.120.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.121.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.121.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.121.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.121.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.121.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.121.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.122.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.122.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.122.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.122.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.122.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.122.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.123.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.123.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.123.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.123.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.123.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.123.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.124.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.124.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.124.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.124.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.124.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.124.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.125.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.125.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.125.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.125.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.125.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.125.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.126.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.126.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.126.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.126.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.126.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.126.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.127.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.127.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.127.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.127.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.127.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.127.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.13.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.13.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.13.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.14.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.14.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.14.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.15.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.15.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.15.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.16.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.16.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.16.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.16.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.16.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.16.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.17.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.17.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.17.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.17.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.17.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.17.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.18.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.18.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.18.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.18.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.18.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.18.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.19.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.19.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.19.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.19.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.19.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.19.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.2.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.2.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.2.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.20.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.20.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.20.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.20.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.20.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.20.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.21.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.21.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.21.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.21.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.21.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.21.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.22.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.22.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.22.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.22.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.22.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.22.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.23.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.23.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.23.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.23.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.23.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.23.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.24.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.24.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.24.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.24.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.24.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.24.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.25.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.25.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.25.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.25.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.25.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.25.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.26.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.26.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.26.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.26.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.26.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.26.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.27.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.27.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.27.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.27.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.27.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.27.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.28.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.28.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.28.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.28.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.28.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.28.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.29.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.29.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.29.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.29.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.29.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.29.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.3.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.3.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.3.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.30.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.30.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.30.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.30.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.30.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.30.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.31.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.31.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.31.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.31.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.31.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.31.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.32.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.32.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.32.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.32.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.32.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.32.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.33.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.33.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.33.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.33.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.33.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.33.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.34.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.34.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.34.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.34.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.34.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.34.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.35.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.35.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.35.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.35.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.35.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.35.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.36.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.36.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.36.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.36.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.36.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.36.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.37.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.37.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.37.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.37.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.37.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.37.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.38.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.38.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.38.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.38.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.38.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.38.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.39.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.39.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.39.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.39.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.39.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.39.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.4.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.4.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.4.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.40.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.40.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.40.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.40.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.40.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.40.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.41.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.41.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.41.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.41.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.41.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.41.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.42.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.42.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.42.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.42.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.42.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.42.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.43.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.43.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.43.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.43.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.43.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.43.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.44.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.44.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.44.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.44.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.44.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.44.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.45.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.45.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.45.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.45.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.45.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.45.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.46.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.46.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.46.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.46.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.46.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.46.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.47.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.47.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.47.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.47.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.47.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.47.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.48.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.48.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.48.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.48.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.48.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.48.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.49.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.49.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.49.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.49.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.49.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.49.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.5.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.5.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.5.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.50.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.50.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.50.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.50.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.50.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.50.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.51.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.51.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.51.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.51.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.51.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.51.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.52.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.52.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.52.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.52.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.52.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.52.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.53.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.53.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.53.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.53.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.53.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.53.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.54.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.54.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.54.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.54.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.54.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.54.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.55.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.55.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.55.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.55.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.55.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.55.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.56.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.56.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.56.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.56.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.56.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.56.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.57.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.57.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.57.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.57.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.57.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.57.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.58.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.58.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.58.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.58.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.58.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.58.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.59.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.59.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.59.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.59.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.59.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.59.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.6.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.6.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.6.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.60.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.60.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.60.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.60.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.60.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.60.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.61.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.61.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.61.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.61.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.61.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.61.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.62.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.62.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.62.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.62.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.62.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.62.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.63.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.63.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.63.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.63.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.63.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.63.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.64.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.64.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.64.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.64.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.64.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.64.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.65.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.65.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.65.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.65.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.65.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.65.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.66.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.66.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.66.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.66.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.66.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.66.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.67.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.67.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.67.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.67.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.67.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.67.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.68.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.68.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.68.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.68.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.68.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.68.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.69.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.69.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.69.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.69.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.69.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.69.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.7.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.7.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.7.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.70.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.70.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.70.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.70.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.70.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.70.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.71.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.71.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.71.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.71.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.71.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.71.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.72.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.72.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.72.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.72.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.72.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.72.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.73.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.73.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.73.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.73.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.73.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.73.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.74.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.74.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.74.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.74.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.74.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.74.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.75.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.75.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.75.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.75.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.75.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.75.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.76.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.76.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.76.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.76.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.76.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.76.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.77.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.77.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.77.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.77.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.77.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.77.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.78.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.78.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.78.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.78.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.78.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.78.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.79.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.79.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.79.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.79.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.79.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.79.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.8.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.8.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.8.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.80.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.80.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.80.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.80.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.80.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.80.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.81.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.81.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.81.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.81.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.81.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.81.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.82.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.82.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.82.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.82.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.82.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.82.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.83.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.83.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.83.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.83.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.83.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.83.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.84.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.84.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.84.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.84.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.84.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.84.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.85.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.85.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.85.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.85.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.85.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.85.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.86.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.86.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.86.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.86.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.86.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.86.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.87.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.87.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.87.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.87.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.87.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.87.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.88.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.88.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.88.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.88.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.88.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.88.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.89.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.89.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.89.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.89.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.89.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.89.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.9.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.9.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.9.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.90.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.90.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.90.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.90.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.90.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.90.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.91.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.91.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.91.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.91.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.91.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.91.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.92.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.92.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.92.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.92.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.92.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.92.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.93.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.93.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.93.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.93.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.93.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.93.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.94.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.94.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.94.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.94.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.94.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.94.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.95.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.95.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.95.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.95.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.95.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.95.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.96.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.96.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.96.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.96.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.96.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.96.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.97.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.97.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.97.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.97.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.97.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.97.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.98.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.98.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.98.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.98.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.98.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.98.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.99.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.99.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.99.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.99.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.99.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.experts.99.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.shared_experts.down_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.shared_experts.gate_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.shared_experts.up_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.input_layernorm.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.post_attention_layernorm.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.index_k_norm.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.index_k_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.index_q_norm.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.index_q_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.k_norm.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.k_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.k_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.o_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.o_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.q_norm.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.q_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.q_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.v_proj.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.16.self_attn.v_proj.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.0.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.0.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.0.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.1.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.1.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.1.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.10.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.10.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.10.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.100.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.100.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.100.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.101.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.101.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.101.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.102.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.102.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.102.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.103.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.103.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.103.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.104.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.104.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.104.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.105.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.105.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.105.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.106.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.106.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.106.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.107.w1.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.107.w2.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00059.safetensors", - "language_model.model.layers.50.block_sparse_moe.experts.107.w3.weight_scale": "model-00016-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.gate.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.108.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.108.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.108.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.108.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.108.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.108.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.109.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.109.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.109.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.109.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.109.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.109.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.11.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.11.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.11.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.11.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.11.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.11.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.110.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.110.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.110.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.110.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.110.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.110.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.111.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.111.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.111.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.111.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.111.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.111.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.112.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.112.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.112.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.112.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.112.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.112.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.113.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.113.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.113.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.113.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.113.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.113.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.114.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.114.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.114.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.114.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.114.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.114.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.115.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.115.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.115.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.115.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.115.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.115.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.116.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.116.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.116.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.116.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.116.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.116.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.117.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.117.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.117.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.117.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.117.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.117.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.118.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.118.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.118.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.118.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.118.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.118.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.119.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.119.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.119.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.119.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.119.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.119.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.12.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.12.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.12.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.12.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.12.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.12.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.120.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.120.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.120.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.120.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.120.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.120.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.121.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.121.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.121.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.121.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.121.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.121.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.122.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.122.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.122.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.122.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.122.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.122.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.123.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.123.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.123.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.123.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.123.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.123.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.124.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.124.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.124.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.124.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.124.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.124.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.125.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.125.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.125.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.125.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.125.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.125.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.126.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.126.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.126.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.126.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.126.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.126.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.127.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.127.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.127.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.127.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.127.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.127.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.13.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.13.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.13.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.13.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.13.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.13.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.14.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.14.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.14.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.14.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.14.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.14.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.15.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.15.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.15.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.15.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.15.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.15.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.16.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.16.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.16.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.16.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.16.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.16.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.17.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.17.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.17.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.17.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.17.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.17.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.18.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.18.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.18.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.18.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.18.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.18.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.19.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.19.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.19.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.19.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.19.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.19.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.2.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.2.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.2.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.20.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.20.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.20.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.20.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.20.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.20.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.21.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.21.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.21.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.21.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.21.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.21.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.22.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.22.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.22.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.22.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.22.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.22.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.23.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.23.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.23.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.23.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.23.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.23.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.24.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.24.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.24.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.24.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.24.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.24.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.25.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.25.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.25.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.25.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.25.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.25.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.26.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.26.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.26.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.26.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.26.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.26.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.27.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.27.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.27.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.27.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.27.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.27.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.28.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.28.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.28.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.28.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.28.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.28.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.29.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.29.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.29.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.29.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.29.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.29.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.3.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.3.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.3.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.30.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.30.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.30.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.30.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.30.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.30.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.31.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.31.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.31.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.31.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.31.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.31.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.32.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.32.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.32.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.32.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.32.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.32.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.33.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.33.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.33.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.33.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.33.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.33.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.34.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.34.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.34.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.34.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.34.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.34.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.35.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.35.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.35.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.35.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.35.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.35.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.36.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.36.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.36.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.36.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.36.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.36.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.37.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.37.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.37.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.37.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.37.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.37.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.38.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.38.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.38.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.38.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.38.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.38.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.39.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.39.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.39.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.39.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.39.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.39.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.4.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.4.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.4.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.4.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.4.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.4.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.40.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.40.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.40.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.40.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.40.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.40.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.41.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.41.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.41.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.41.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.41.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.41.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.42.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.42.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.42.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.42.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.42.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.42.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.43.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.43.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.43.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.43.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.43.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.43.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.44.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.44.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.44.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.44.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.44.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.44.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.45.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.45.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.45.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.45.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.45.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.45.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.46.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.46.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.46.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.46.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.46.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.46.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.47.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.47.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.47.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.47.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.47.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.47.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.48.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.48.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.48.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.48.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.48.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.48.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.49.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.49.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.49.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.49.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.49.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.49.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.5.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.5.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.5.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.5.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.50.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.50.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.50.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.50.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.50.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.50.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.51.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.51.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.51.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.51.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.51.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.51.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.52.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.52.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.52.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.52.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.52.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.52.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.53.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.53.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.53.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.53.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.53.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.53.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.54.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.54.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.54.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.54.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.54.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.54.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.55.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.55.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.55.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.55.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.55.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.55.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.56.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.56.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.56.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.56.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.56.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.56.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.57.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.57.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.57.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.57.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.57.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.57.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.58.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.58.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.58.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.58.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.58.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.58.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.59.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.59.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.59.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.59.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.59.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.59.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.6.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.6.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.6.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.60.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.60.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.60.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.60.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.60.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.60.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.61.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.61.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.61.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.61.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.61.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.61.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.62.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.62.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.62.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.62.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.62.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.62.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.63.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.63.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.63.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.63.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.63.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.63.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.64.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.64.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.64.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.64.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.64.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.64.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.65.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.65.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.65.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.65.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.65.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.65.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.66.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.66.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.66.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.66.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.66.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.66.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.67.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.67.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.67.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.67.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.67.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.67.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.68.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.68.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.68.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.68.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.68.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.68.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.69.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.69.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.69.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.69.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.69.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.69.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.7.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.7.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.7.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.7.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.70.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.70.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.70.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.70.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.70.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.70.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.71.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.71.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.71.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.71.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.71.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.71.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.72.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.72.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.72.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.72.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.72.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.72.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.73.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.73.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.73.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.73.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.73.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.73.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.74.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.74.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.74.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.74.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.74.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.74.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.75.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.75.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.75.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.75.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.75.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.75.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.76.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.76.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.76.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.76.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.76.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.76.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.77.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.77.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.77.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.77.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.77.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.77.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.78.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.78.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.78.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.78.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.78.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.78.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.79.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.79.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.79.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.79.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.79.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.79.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.8.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.8.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.8.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.8.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.8.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.8.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.80.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.80.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.80.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.80.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.80.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.80.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.81.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.81.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.81.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.81.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.81.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.81.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.82.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.82.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.82.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.82.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.82.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.82.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.83.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.83.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.83.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.83.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.83.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.83.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.84.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.84.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.84.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.84.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.84.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.84.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.85.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.85.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.85.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.85.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.85.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.85.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.86.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.86.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.86.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.86.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.86.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.86.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.87.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.87.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.87.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.87.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.87.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.87.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.88.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.88.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.88.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.88.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.88.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.88.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.89.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.89.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.89.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.89.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.89.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.89.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.9.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.9.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.9.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.9.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.9.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.9.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.90.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.90.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.90.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.90.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.90.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.90.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.91.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.91.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.91.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.91.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.91.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.91.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.92.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.92.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.92.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.92.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.92.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.92.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.93.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.93.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.93.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.93.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.93.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.93.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.94.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.94.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.94.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.94.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.94.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.94.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.95.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.95.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.95.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.95.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.95.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.95.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.96.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.96.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.96.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.96.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.96.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.96.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.97.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.97.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.97.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.97.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.97.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.97.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.98.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.98.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.98.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.98.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.98.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.98.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.99.w1.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.99.w1.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.99.w2.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.99.w2.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.99.w3.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.experts.99.w3.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.shared_experts.down_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.shared_experts.gate_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.shared_experts.up_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.input_layernorm.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.post_attention_layernorm.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.index_k_norm.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.index_k_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.index_q_norm.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.index_q_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.k_norm.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.k_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.k_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.o_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.o_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.q_norm.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.q_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.q_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.v_proj.weight": "model-00042-of-00059.safetensors", - "language_model.model.layers.42.self_attn.v_proj.weight_scale": "model-00042-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.gate.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.108.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.108.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.108.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.108.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.108.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.108.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.109.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.109.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.109.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.109.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.109.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.109.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.11.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.11.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.11.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.11.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.11.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.11.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.110.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.110.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.110.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.110.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.110.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.110.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.111.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.111.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.111.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.111.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.111.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.111.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.112.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.112.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.112.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.112.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.112.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.112.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.113.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.113.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.113.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.113.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.113.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.113.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.114.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.114.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.114.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.114.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.114.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.114.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.115.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.115.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.115.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.115.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.115.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.115.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.116.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.116.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.116.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.116.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.116.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.116.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.117.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.117.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.117.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.117.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.117.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.117.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.118.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.118.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.118.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.118.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.118.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.118.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.119.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.119.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.119.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.119.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.119.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.119.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.12.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.12.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.12.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.12.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.12.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.12.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.120.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.120.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.120.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.120.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.120.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.120.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.121.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.121.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.121.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.121.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.121.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.121.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.122.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.122.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.122.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.122.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.122.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.122.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.123.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.123.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.123.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.123.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.123.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.123.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.124.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.124.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.124.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.124.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.124.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.124.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.125.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.125.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.125.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.125.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.125.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.125.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.126.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.126.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.126.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.126.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.126.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.126.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.127.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.127.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.127.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.127.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.127.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.127.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.13.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.13.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.13.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.13.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.13.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.13.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.14.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.14.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.14.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.14.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.14.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.14.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.15.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.15.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.15.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.15.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.15.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.15.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.16.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.16.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.16.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.16.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.16.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.16.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.17.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.17.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.17.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.17.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.17.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.17.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.18.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.18.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.18.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.18.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.18.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.18.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.19.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.19.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.19.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.19.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.19.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.19.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.2.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.2.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.2.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.20.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.20.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.20.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.20.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.20.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.20.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.21.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.21.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.21.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.21.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.21.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.21.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.22.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.22.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.22.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.22.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.22.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.22.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.23.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.23.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.23.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.23.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.23.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.23.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.24.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.24.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.24.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.24.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.24.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.24.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.25.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.25.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.25.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.25.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.25.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.25.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.26.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.26.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.26.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.26.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.26.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.26.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.27.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.27.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.27.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.27.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.27.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.27.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.28.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.28.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.28.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.28.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.28.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.28.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.29.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.29.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.29.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.29.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.29.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.29.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.3.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.3.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.3.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.3.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.3.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.3.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.30.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.30.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.30.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.30.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.30.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.30.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.31.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.31.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.31.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.31.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.31.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.31.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.32.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.32.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.32.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.32.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.32.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.32.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.33.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.33.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.33.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.33.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.33.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.33.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.34.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.34.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.34.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.34.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.34.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.34.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.35.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.35.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.35.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.35.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.35.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.35.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.36.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.36.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.36.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.36.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.36.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.36.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.37.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.37.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.37.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.37.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.37.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.37.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.38.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.38.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.38.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.38.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.38.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.38.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.39.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.39.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.39.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.39.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.39.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.39.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.4.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.4.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.4.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.4.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.4.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.4.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.40.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.40.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.40.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.40.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.40.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.40.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.41.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.41.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.41.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.41.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.41.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.41.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.42.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.42.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.42.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.42.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.42.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.42.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.43.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.43.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.43.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.43.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.43.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.43.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.44.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.44.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.44.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.44.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.44.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.44.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.45.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.45.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.45.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.45.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.45.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.45.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.46.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.46.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.46.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.46.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.46.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.46.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.47.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.47.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.47.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.47.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.47.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.47.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.48.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.48.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.48.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.48.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.48.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.48.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.49.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.49.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.49.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.49.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.49.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.49.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.5.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.5.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.5.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.5.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.5.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.5.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.50.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.50.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.50.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.50.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.50.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.50.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.51.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.51.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.51.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.51.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.51.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.51.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.52.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.52.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.52.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.52.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.52.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.52.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.53.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.53.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.53.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.53.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.53.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.53.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.54.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.54.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.54.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.54.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.54.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.54.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.55.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.55.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.55.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.55.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.55.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.55.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.56.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.56.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.56.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.56.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.56.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.56.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.57.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.57.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.57.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.57.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.57.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.57.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.58.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.58.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.58.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.58.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.58.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.58.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.59.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.59.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.59.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.59.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.59.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.59.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.6.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.6.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.6.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.6.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.6.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.6.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.60.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.60.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.60.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.60.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.60.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.60.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.61.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.61.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.61.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.61.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.61.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.61.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.62.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.62.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.62.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.62.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.62.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.62.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.63.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.63.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.63.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.63.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.63.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.63.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.64.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.64.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.64.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.64.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.64.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.64.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.65.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.65.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.65.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.65.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.65.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.65.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.66.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.66.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.66.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.66.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.66.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.66.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.67.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.67.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.67.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.67.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.67.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.67.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.68.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.68.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.68.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.68.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.68.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.68.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.69.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.69.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.69.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.69.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.69.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.69.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.7.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.7.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.7.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.7.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.7.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.7.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.70.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.70.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.70.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.70.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.70.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.70.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.71.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.71.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.71.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.71.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.71.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.71.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.72.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.72.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.72.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.72.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.72.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.72.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.73.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.73.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.73.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.73.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.73.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.73.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.74.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.74.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.74.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.74.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.74.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.74.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.75.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.75.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.75.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.75.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.75.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.75.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.76.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.76.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.76.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.76.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.76.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.76.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.77.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.77.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.77.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.77.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.77.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.77.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.78.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.78.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.78.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.78.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.78.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.78.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.79.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.79.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.79.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.79.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.79.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.79.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.8.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.8.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.8.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.8.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.8.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.8.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.80.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.80.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.80.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.80.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.80.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.80.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.81.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.81.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.81.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.81.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.81.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.81.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.82.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.82.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.82.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.82.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.82.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.82.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.83.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.83.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.83.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.83.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.83.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.83.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.84.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.84.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.84.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.84.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.84.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.84.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.85.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.85.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.85.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.85.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.85.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.85.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.86.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.86.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.86.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.86.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.86.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.86.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.87.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.87.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.87.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.87.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.87.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.87.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.88.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.88.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.88.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.88.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.88.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.88.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.89.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.89.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.89.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.89.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.89.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.89.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.9.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.9.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.9.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.9.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.9.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.9.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.90.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.90.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.90.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.90.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.90.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.90.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.91.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.91.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.91.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.91.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.91.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.91.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.92.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.92.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.92.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.92.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.92.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.92.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.93.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.93.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.93.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.93.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.93.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.93.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.94.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.94.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.94.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.94.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.94.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.94.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.95.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.95.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.95.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.95.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.95.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.95.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.96.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.96.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.96.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.96.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.96.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.96.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.97.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.97.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.97.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.97.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.97.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.97.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.98.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.98.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.98.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.98.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.98.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.98.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.99.w1.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.99.w1.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.99.w2.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.99.w2.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.99.w3.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.99.w3.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.shared_experts.down_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.shared_experts.gate_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.shared_experts.up_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.input_layernorm.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.post_attention_layernorm.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.index_k_norm.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.index_k_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.index_q_norm.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.index_q_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.k_norm.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.k_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.k_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.o_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.o_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.q_norm.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.q_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.q_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.v_proj.weight": "model-00049-of-00059.safetensors", - "language_model.model.layers.49.self_attn.v_proj.weight_scale": "model-00049-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.gate.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.108.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.108.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.108.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.108.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.108.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.108.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.109.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.109.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.109.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.109.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.109.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.109.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.11.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.11.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.11.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.11.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.11.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.11.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.110.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.110.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.110.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.110.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.110.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.110.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.111.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.111.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.111.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.111.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.111.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.111.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.112.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.112.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.112.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.112.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.112.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.112.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.113.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.113.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.113.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.113.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.113.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.113.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.114.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.114.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.114.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.114.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.114.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.114.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.115.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.115.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.115.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.115.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.115.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.115.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.116.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.116.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.116.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.116.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.116.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.116.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.117.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.117.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.117.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.117.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.117.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.117.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.118.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.118.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.118.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.118.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.118.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.118.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.119.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.119.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.119.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.119.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.119.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.119.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.12.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.12.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.12.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.12.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.12.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.12.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.120.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.120.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.120.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.120.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.120.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.120.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.121.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.121.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.121.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.121.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.121.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.121.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.122.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.122.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.122.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.122.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.122.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.122.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.123.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.123.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.123.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.123.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.123.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.123.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.124.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.124.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.124.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.124.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.124.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.124.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.125.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.125.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.125.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.125.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.125.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.125.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.126.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.126.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.126.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.126.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.126.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.126.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.127.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.127.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.127.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.127.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.127.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.127.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.13.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.13.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.13.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.13.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.13.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.13.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.14.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.14.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.14.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.14.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.14.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.14.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.15.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.15.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.15.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.15.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.15.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.15.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.16.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.16.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.16.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.16.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.16.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.16.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.17.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.17.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.17.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.17.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.17.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.17.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.18.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.18.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.18.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.18.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.18.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.18.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.19.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.19.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.19.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.19.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.19.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.19.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.2.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.2.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.2.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.20.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.20.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.20.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.20.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.20.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.20.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.21.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.21.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.21.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.21.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.21.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.21.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.22.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.22.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.22.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.22.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.22.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.22.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.23.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.23.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.23.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.23.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.23.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.23.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.24.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.24.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.24.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.24.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.24.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.24.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.25.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.25.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.25.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.25.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.25.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.25.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.26.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.26.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.26.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.26.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.26.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.26.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.27.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.27.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.27.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.27.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.27.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.27.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.28.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.28.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.28.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.28.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.28.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.28.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.29.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.29.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.29.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.29.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.29.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.29.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.3.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.3.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.3.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.3.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.3.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.3.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.30.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.30.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.30.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.30.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.30.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.30.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.31.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.31.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.31.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.31.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.31.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.31.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.32.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.32.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.32.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.32.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.32.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.32.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.33.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.33.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.33.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.33.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.33.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.33.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.34.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.34.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.34.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.34.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.34.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.34.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.35.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.35.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.35.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.35.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.35.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.35.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.36.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.36.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.36.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.36.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.36.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.36.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.37.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.37.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.37.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.37.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.37.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.37.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.38.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.38.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.38.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.38.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.38.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.38.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.39.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.39.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.39.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.39.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.39.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.39.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.4.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.4.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.4.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.4.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.4.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.4.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.40.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.40.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.40.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.40.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.40.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.40.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.41.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.41.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.41.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.41.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.41.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.41.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.42.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.42.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.42.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.42.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.42.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.42.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.43.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.43.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.43.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.43.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.43.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.43.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.44.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.44.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.44.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.44.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.44.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.44.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.45.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.45.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.45.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.45.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.45.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.45.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.46.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.46.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.46.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.46.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.46.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.46.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.47.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.47.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.47.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.47.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.47.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.47.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.48.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.48.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.48.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.48.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.48.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.48.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.49.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.49.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.49.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.49.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.49.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.49.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.5.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.5.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.5.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.5.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.5.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.5.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.50.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.50.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.50.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.50.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.50.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.50.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.51.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.51.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.51.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.51.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.51.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.51.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.52.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.52.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.52.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.52.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.52.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.52.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.53.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.53.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.53.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.53.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.53.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.53.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.54.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.54.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.54.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.54.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.54.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.54.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.55.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.55.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.55.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.55.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.55.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.55.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.56.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.56.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.56.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.56.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.56.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.56.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.57.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.57.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.57.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.57.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.57.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.57.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.58.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.58.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.58.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.58.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.58.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.58.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.59.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.59.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.59.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.59.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.59.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.59.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.6.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.6.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.6.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.6.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.6.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.6.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.60.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.60.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.60.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.60.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.60.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.60.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.61.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.61.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.61.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.61.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.61.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.61.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.62.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.62.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.62.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.62.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.62.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.62.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.63.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.63.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.63.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.63.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.63.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.63.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.64.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.64.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.64.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.64.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.64.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.64.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.65.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.65.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.65.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.65.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.65.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.65.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.66.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.66.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.66.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.66.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.66.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.66.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.67.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.67.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.67.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.67.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.67.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.67.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.68.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.68.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.68.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.68.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.68.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.68.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.69.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.69.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.69.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.69.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.69.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.69.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.7.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.7.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.7.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.7.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.7.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.7.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.70.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.70.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.70.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.70.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.70.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.70.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.71.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.71.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.71.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.71.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.71.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.71.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.72.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.72.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.72.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.72.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.72.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.72.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.73.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.73.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.73.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.73.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.73.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.73.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.74.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.74.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.74.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.74.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.74.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.74.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.75.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.75.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.75.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.75.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.75.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.75.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.76.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.76.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.76.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.76.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.76.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.76.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.77.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.77.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.77.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.77.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.77.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.77.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.78.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.78.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.78.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.78.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.78.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.78.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.79.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.79.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.79.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.79.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.79.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.79.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.8.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.8.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.8.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.8.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.8.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.8.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.80.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.80.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.80.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.80.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.80.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.80.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.81.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.81.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.81.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.81.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.81.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.81.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.82.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.82.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.82.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.82.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.82.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.82.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.83.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.83.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.83.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.83.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.83.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.83.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.84.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.84.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.84.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.84.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.84.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.84.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.85.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.85.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.85.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.85.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.85.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.85.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.86.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.86.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.86.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.86.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.86.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.86.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.87.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.87.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.87.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.87.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.87.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.87.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.88.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.88.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.88.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.88.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.88.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.88.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.89.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.89.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.89.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.89.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.89.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.89.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.9.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.9.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.9.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.9.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.9.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.9.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.90.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.90.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.90.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.90.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.90.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.90.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.91.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.91.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.91.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.91.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.91.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.91.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.92.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.92.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.92.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.92.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.92.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.92.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.93.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.93.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.93.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.93.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.93.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.93.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.94.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.94.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.94.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.94.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.94.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.94.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.95.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.95.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.95.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.95.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.95.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.95.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.96.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.96.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.96.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.96.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.96.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.96.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.97.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.97.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.97.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.97.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.97.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.97.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.98.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.98.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.98.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.98.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.98.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.98.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.99.w1.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.99.w1.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.99.w2.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.99.w2.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.99.w3.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.99.w3.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.shared_experts.down_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.shared_experts.gate_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.shared_experts.up_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.input_layernorm.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.post_attention_layernorm.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.index_k_norm.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.index_k_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.index_q_norm.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.index_q_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.k_norm.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.k_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.k_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.o_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.o_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.q_norm.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.q_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.q_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.v_proj.weight": "model-00054-of-00059.safetensors", - "language_model.model.layers.54.self_attn.v_proj.weight_scale": "model-00054-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.e_score_correction_bias": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.e_score_correction_bias": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.0.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.0.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.0.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.1.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.1.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.1.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.10.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.10.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.10.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.100.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.100.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.100.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.101.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.101.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.101.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.102.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.102.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.102.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.103.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.103.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.103.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.104.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.104.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.104.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.105.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.105.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.105.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.106.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.106.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.106.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.107.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.107.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.107.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.108.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.108.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.108.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.108.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.108.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.108.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.109.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.109.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.109.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.109.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.109.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.109.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.11.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.11.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.11.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.110.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.110.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.110.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.110.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.110.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.110.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.111.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.111.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.111.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.111.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.111.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.111.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.112.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.112.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.112.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.112.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.112.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.112.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.113.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.113.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.113.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.113.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.113.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.113.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.114.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.114.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.114.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.114.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.114.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.114.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.115.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.115.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.115.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.115.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.115.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.115.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.116.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.116.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.116.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.116.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.116.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.116.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.117.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.117.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.117.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.117.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.117.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.117.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.118.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.118.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.118.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.118.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.118.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.118.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.119.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.119.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.119.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.119.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.119.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.119.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.12.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.12.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.12.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.120.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.120.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.120.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.120.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.120.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.120.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.121.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.121.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.121.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.121.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.121.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.121.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.122.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.122.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.122.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.122.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.122.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.122.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.123.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.123.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.123.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.123.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.123.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.123.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.124.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.124.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.124.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.124.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.124.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.124.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.125.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.125.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.125.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.125.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.125.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.125.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.126.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.126.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.126.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.126.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.126.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.126.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.127.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.127.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.127.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.127.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.127.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.127.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.13.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.13.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.13.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.14.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.14.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.14.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.15.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.15.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.15.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.16.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.16.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.16.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.17.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.17.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.17.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.18.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.18.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.18.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.19.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.19.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.19.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.2.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.2.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.2.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.20.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.20.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.20.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.21.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.21.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.21.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.22.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.22.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.22.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.23.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.23.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.23.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.24.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.24.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.24.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.25.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.25.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.25.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.26.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.26.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.26.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.27.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.27.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.27.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.28.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.28.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.28.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.29.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.29.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.29.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.3.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.3.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.3.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.30.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.30.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.30.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.31.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.31.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.31.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.32.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.32.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.32.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.32.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.32.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.32.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.33.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.33.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.33.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.33.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.33.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.33.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.34.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.34.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.34.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.34.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.34.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.34.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.35.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.35.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.35.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.35.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.35.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.35.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.36.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.36.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.36.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.36.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.36.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.36.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.37.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.37.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.37.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.37.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.37.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.37.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.38.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.38.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.38.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.38.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.38.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.38.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.39.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.39.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.39.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.39.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.39.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.39.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.4.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.4.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.4.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.40.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.40.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.40.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.40.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.40.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.40.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.41.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.41.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.41.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.41.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.41.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.41.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.42.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.42.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.42.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.42.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.42.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.42.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.43.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.43.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.43.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.43.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.43.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.43.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.44.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.44.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.44.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.44.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.44.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.44.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.45.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.45.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.45.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.45.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.45.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.45.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.46.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.46.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.46.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.46.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.46.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.46.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.47.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.47.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.47.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.47.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.47.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.47.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.48.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.48.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.48.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.48.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.48.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.48.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.49.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.49.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.49.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.49.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.49.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.49.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.5.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.5.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.5.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.50.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.50.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.50.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.50.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.50.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.50.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.51.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.51.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.51.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.51.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.51.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.51.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.52.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.52.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.52.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.52.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.52.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.52.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.53.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.53.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.53.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.53.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.53.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.53.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.54.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.54.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.54.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.54.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.54.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.54.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.55.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.55.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.55.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.55.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.55.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.55.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.56.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.56.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.56.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.56.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.56.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.56.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.57.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.57.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.57.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.57.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.57.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.57.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.58.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.58.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.58.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.58.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.58.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.58.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.59.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.59.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.59.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.59.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.59.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.59.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.6.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.6.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.6.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.60.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.60.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.60.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.60.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.60.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.60.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.61.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.61.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.61.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.61.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.61.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.61.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.62.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.62.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.62.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.62.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.62.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.62.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.63.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.63.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.63.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.63.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.63.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.63.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.64.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.64.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.64.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.64.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.64.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.64.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.65.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.65.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.65.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.65.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.65.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.65.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.66.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.66.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.66.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.66.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.66.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.66.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.67.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.67.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.67.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.67.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.67.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.67.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.68.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.68.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.68.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.68.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.68.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.68.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.69.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.69.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.69.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.69.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.69.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.69.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.7.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.7.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.7.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.70.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.70.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.70.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.70.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.70.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.70.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.71.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.71.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.71.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.71.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.71.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.71.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.72.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.72.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.72.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.72.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.72.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.72.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.73.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.73.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.73.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.73.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.73.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.73.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.74.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.74.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.74.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.74.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.74.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.74.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.75.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.75.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.75.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.75.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.75.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.75.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.76.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.76.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.76.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.76.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.76.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.76.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.77.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.77.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.77.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.77.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.77.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.77.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.78.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.78.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.78.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.78.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.78.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.78.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.79.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.79.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.79.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.79.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.79.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.79.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.8.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.8.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.8.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.80.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.80.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.80.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.80.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.80.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.80.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.81.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.81.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.81.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.81.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.81.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.81.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.82.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.82.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.82.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.82.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.82.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.82.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.83.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.83.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.83.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.83.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.83.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.83.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.84.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.84.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.84.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.84.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.84.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.84.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.85.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.85.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.85.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.85.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.85.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.85.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.86.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.86.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.86.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.86.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.86.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.86.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.87.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.87.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.87.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.87.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.87.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.87.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.88.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.88.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.88.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.88.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.88.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.88.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.89.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.89.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.89.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.89.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.89.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.89.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.9.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.9.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.9.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.90.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.90.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.90.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.90.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.90.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.90.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.91.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.91.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.91.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.91.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.91.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.91.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.92.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.92.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.92.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.92.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.92.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.92.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.93.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.93.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.93.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.93.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.93.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.93.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.94.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.94.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.94.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.94.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.94.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.94.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.95.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.95.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.95.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.95.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.95.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.95.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.96.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.96.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.96.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.96.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.96.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.96.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.97.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.97.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.97.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.97.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.97.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.97.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.98.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.98.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.98.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.98.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.98.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.98.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.99.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.99.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.99.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.99.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.99.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.experts.99.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.shared_experts.down_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.shared_experts.gate_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.shared_experts.up_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.input_layernorm.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.post_attention_layernorm.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.index_k_norm.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.index_k_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.index_q_norm.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.index_q_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.k_norm.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.k_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.k_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.o_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.o_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.q_norm.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.q_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.q_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.v_proj.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.13.self_attn.v_proj.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.0.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.0.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.0.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.1.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.1.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.1.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.10.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.10.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.10.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.100.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.100.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.100.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.101.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.101.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.101.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.102.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.102.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.102.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.103.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.103.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.103.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.104.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.104.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.104.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.105.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.105.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.105.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.106.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.106.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.106.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.107.w1.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.107.w2.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.107.w3.weight_scale": "model-00013-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.e_score_correction_bias": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.gate.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.e_score_correction_bias": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.0.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.0.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.0.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.1.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.1.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.1.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.10.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.10.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.10.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.10.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.10.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.10.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.100.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.100.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.100.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.100.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.100.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.100.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.101.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.101.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.101.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.101.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.101.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.101.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.102.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.102.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.102.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.102.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.102.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.102.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.103.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.103.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.103.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.103.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.103.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.103.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.104.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.104.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.104.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.104.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.104.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.104.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.105.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.105.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.105.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.105.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.105.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.105.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.106.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.106.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.106.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.106.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.106.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.106.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.107.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.107.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.107.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.107.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.107.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.107.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.108.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.108.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.108.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.108.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.108.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.108.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.109.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.109.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.109.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.109.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.109.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.109.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.11.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.11.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.11.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.11.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.11.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.11.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.110.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.110.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.110.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.110.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.110.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.110.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.111.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.111.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.111.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.111.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.111.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.111.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.112.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.112.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.112.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.112.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.112.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.112.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.113.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.113.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.113.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.113.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.113.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.113.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.114.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.114.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.114.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.114.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.114.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.114.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.115.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.115.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.115.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.115.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.115.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.115.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.116.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.116.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.116.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.116.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.116.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.116.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.117.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.117.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.117.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.117.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.117.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.117.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.118.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.118.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.118.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.118.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.118.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.118.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.119.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.119.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.119.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.119.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.119.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.119.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.12.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.12.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.12.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.12.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.12.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.12.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.120.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.120.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.120.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.120.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.120.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.120.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.121.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.121.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.121.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.121.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.121.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.121.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.122.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.122.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.122.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.122.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.122.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.122.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.123.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.123.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.123.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.123.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.123.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.123.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.124.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.124.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.124.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.124.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.124.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.124.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.125.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.125.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.125.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.125.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.125.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.125.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.126.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.126.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.126.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.126.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.126.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.126.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.127.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.127.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.127.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.127.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.127.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.127.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.13.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.13.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.13.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.13.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.13.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.13.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.14.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.14.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.14.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.14.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.14.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.14.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.15.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.15.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.15.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.15.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.15.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.15.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.16.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.16.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.16.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.16.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.16.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.16.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.17.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.17.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.17.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.17.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.17.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.17.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.18.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.18.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.18.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.18.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.18.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.18.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.19.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.19.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.19.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.19.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.19.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.19.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.2.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.2.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.2.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.20.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.20.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.20.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.20.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.20.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.20.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.21.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.21.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.21.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.21.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.21.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.21.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.22.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.22.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.22.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.22.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.22.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.22.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.23.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.23.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.23.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.23.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.23.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.23.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.24.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.24.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.24.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.24.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.24.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.24.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.25.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.25.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.25.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.25.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.25.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.25.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.26.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.26.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.26.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.26.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.26.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.26.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.27.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.27.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.27.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.27.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.27.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.27.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.28.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.28.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.28.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.28.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.28.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.28.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.29.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.29.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.29.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.29.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.29.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.29.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.3.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.3.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.3.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.30.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.30.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.30.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.30.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.30.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.30.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.31.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.31.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.31.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.31.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.31.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.31.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.32.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.32.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.32.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.32.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.32.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.32.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.33.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.33.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.33.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.33.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.33.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.33.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.34.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.34.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.34.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.34.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.34.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.34.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.35.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.35.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.35.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.35.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.35.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.35.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.36.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.36.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.36.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.36.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.36.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.36.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.37.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.37.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.37.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.37.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.37.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.37.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.38.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.38.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.38.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.38.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.38.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.38.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.39.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.39.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.39.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.39.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.39.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.39.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.4.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.4.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.4.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.40.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.40.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.40.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.40.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.40.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.40.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.41.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.41.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.41.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.41.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.41.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.41.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.42.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.42.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.42.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.42.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.42.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.42.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.43.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.43.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.43.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.43.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.43.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.43.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.44.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.44.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.44.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.44.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.44.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.44.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.45.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.45.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.45.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.45.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.45.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.45.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.46.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.46.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.46.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.46.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.46.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.46.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.47.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.47.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.47.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.47.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.47.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.47.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.48.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.48.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.48.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.48.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.48.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.48.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.49.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.49.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.49.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.49.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.49.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.49.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.5.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.5.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.5.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.50.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.50.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.50.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.50.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.50.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.50.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.51.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.51.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.51.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.51.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.51.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.51.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.52.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.52.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.52.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.52.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.52.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.52.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.53.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.53.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.53.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.53.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.53.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.53.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.54.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.54.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.54.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.54.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.54.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.54.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.55.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.55.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.55.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.55.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.55.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.55.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.56.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.56.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.56.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.56.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.56.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.56.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.57.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.57.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.57.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.57.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.57.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.57.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.58.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.58.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.58.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.58.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.58.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.58.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.59.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.59.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.59.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.59.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.59.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.59.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.6.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.6.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.6.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.60.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.60.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.60.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.60.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.60.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.60.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.61.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.61.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.61.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.61.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.61.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.61.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.62.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.62.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.62.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.62.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.62.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.62.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.63.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.63.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.63.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.63.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.63.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.63.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.64.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.64.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.64.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.64.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.64.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.64.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.65.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.65.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.65.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.65.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.65.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.65.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.66.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.66.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.66.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.66.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.66.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.66.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.67.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.67.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.67.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.67.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.67.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.67.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.68.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.68.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.68.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.68.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.68.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.68.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.69.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.69.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.69.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.69.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.69.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.69.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.7.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.7.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.7.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.70.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.70.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.70.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.70.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.70.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.70.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.71.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.71.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.71.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.71.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.71.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.71.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.72.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.72.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.72.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.72.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.72.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.72.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.73.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.73.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.73.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.73.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.73.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.73.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.74.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.74.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.74.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.74.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.74.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.74.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.75.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.75.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.75.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.75.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.75.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.75.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.76.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.76.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.76.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.76.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.76.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.76.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.77.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.77.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.77.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.77.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.77.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.77.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.78.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.78.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.78.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.78.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.78.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.78.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.79.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.79.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.79.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.79.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.79.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.79.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.8.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.8.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.8.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.8.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.8.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.8.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.80.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.80.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.80.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.80.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.80.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.80.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.81.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.81.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.81.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.81.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.81.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.81.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.82.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.82.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.82.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.82.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.82.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.82.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.83.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.83.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.83.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.83.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.83.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.83.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.84.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.84.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.84.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.84.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.84.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.84.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.85.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.85.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.85.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.85.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.85.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.85.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.86.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.86.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.86.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.86.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.86.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.86.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.87.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.87.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.87.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.87.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.87.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.87.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.88.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.88.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.88.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.88.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.88.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.88.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.89.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.89.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.89.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.89.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.89.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.89.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.9.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.9.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.9.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.9.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.9.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.9.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.90.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.90.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.90.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.90.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.90.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.90.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.91.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.91.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.91.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.91.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.91.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.91.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.92.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.92.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.92.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.92.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.92.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.92.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.93.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.93.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.93.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.93.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.93.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.93.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.94.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.94.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.94.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.94.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.94.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.94.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.95.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.95.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.95.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.95.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.95.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.95.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.96.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.96.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.96.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.96.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.96.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.96.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.97.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.97.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.97.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.97.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.97.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.97.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.98.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.98.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.98.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.98.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.98.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.98.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.99.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.99.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.99.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.99.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.99.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.experts.99.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.shared_experts.down_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.shared_experts.gate_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.shared_experts.up_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.input_layernorm.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.post_attention_layernorm.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.index_k_norm.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.index_k_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.index_q_norm.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.index_q_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.k_norm.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.k_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.k_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.o_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.o_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.q_norm.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.q_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.q_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.v_proj.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.21.self_attn.v_proj.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.0.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.0.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.0.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.1.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.1.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.1.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.10.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.10.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.10.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.10.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.10.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.10.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.100.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.100.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.100.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.100.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.100.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.100.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.101.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.101.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.101.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.101.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.101.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.101.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.102.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.102.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.102.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.102.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.102.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.102.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.103.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.103.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.103.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.103.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.103.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.103.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.104.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.104.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.104.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.104.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.104.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.104.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.105.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.105.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.105.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.105.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.105.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.105.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.106.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.106.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.106.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.106.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.106.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.106.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.107.w1.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.107.w1.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.107.w2.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.107.w2.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.107.w3.weight": "model-00021-of-00059.safetensors", - "language_model.model.layers.55.block_sparse_moe.experts.107.w3.weight_scale": "model-00021-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.gate.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.108.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.108.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.108.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.108.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.108.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.108.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.109.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.109.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.109.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.109.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.109.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.109.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.11.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.11.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.11.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.11.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.11.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.11.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.110.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.110.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.110.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.110.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.110.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.110.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.111.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.111.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.111.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.111.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.111.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.111.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.112.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.112.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.112.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.112.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.112.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.112.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.113.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.113.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.113.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.113.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.113.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.113.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.114.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.114.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.114.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.114.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.114.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.114.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.115.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.115.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.115.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.115.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.115.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.115.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.116.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.116.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.116.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.116.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.116.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.116.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.117.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.117.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.117.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.117.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.117.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.117.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.118.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.118.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.118.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.118.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.118.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.118.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.119.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.119.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.119.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.119.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.119.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.119.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.12.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.12.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.12.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.12.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.12.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.12.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.120.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.120.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.120.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.120.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.120.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.120.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.121.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.121.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.121.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.121.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.121.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.121.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.122.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.122.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.122.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.122.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.122.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.122.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.123.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.123.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.123.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.123.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.123.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.123.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.124.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.124.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.124.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.124.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.124.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.124.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.125.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.125.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.125.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.125.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.125.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.125.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.126.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.126.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.126.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.126.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.126.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.126.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.127.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.127.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.127.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.127.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.127.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.127.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.13.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.13.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.13.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.13.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.13.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.13.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.14.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.14.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.14.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.14.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.14.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.14.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.15.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.15.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.15.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.15.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.15.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.15.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.16.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.16.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.16.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.16.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.16.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.16.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.17.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.17.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.17.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.17.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.17.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.17.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.18.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.18.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.18.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.18.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.18.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.18.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.19.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.19.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.19.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.19.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.19.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.19.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.2.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.2.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.2.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.20.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.20.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.20.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.20.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.20.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.20.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.21.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.21.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.21.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.21.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.21.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.21.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.22.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.22.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.22.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.22.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.22.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.22.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.23.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.23.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.23.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.23.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.23.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.23.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.24.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.24.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.24.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.24.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.24.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.24.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.25.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.25.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.25.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.25.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.25.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.25.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.26.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.26.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.26.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.26.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.26.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.26.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.27.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.27.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.27.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.27.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.27.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.27.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.28.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.28.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.28.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.28.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.28.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.28.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.29.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.29.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.29.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.29.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.29.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.29.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.3.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.3.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.3.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.30.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.30.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.30.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.30.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.30.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.30.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.31.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.31.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.31.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.31.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.31.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.31.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.32.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.32.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.32.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.32.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.32.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.32.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.33.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.33.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.33.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.33.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.33.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.33.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.34.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.34.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.34.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.34.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.34.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.34.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.35.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.35.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.35.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.35.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.35.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.35.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.36.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.36.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.36.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.36.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.36.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.36.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.37.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.37.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.37.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.37.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.37.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.37.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.38.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.38.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.38.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.38.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.38.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.38.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.39.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.39.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.39.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.39.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.39.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.39.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.4.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.4.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.4.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.4.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.4.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.4.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.40.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.40.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.40.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.40.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.40.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.40.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.41.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.41.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.41.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.41.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.41.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.41.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.42.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.42.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.42.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.42.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.42.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.42.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.43.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.43.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.43.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.43.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.43.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.43.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.44.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.44.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.44.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.44.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.44.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.44.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.45.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.45.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.45.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.45.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.45.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.45.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.46.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.46.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.46.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.46.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.46.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.46.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.47.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.47.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.47.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.47.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.47.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.47.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.48.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.48.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.48.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.48.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.48.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.48.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.49.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.49.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.49.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.49.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.49.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.49.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.5.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.5.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.5.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.5.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.5.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.5.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.50.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.50.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.50.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.50.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.50.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.50.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.51.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.51.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.51.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.51.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.51.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.51.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.52.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.52.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.52.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.52.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.52.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.52.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.53.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.53.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.53.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.53.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.53.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.53.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.54.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.54.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.54.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.54.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.54.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.54.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.55.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.55.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.55.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.55.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.55.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.55.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.56.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.56.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.56.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.56.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.56.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.56.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.57.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.57.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.57.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.57.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.57.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.57.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.58.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.58.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.58.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.58.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.58.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.58.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.59.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.59.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.59.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.59.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.59.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.59.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.6.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.6.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.6.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.6.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.6.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.6.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.60.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.60.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.60.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.60.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.60.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.60.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.61.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.61.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.61.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.61.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.61.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.61.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.62.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.62.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.62.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.62.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.62.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.62.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.63.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.63.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.63.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.63.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.63.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.63.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.64.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.64.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.64.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.64.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.64.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.64.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.65.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.65.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.65.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.65.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.65.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.65.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.66.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.66.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.66.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.66.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.66.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.66.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.67.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.67.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.67.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.67.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.67.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.67.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.68.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.68.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.68.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.68.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.68.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.68.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.69.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.69.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.69.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.69.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.69.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.69.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.7.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.7.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.7.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.7.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.7.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.7.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.70.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.70.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.70.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.70.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.70.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.70.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.71.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.71.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.71.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.71.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.71.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.71.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.72.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.72.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.72.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.72.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.72.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.72.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.73.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.73.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.73.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.73.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.73.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.73.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.74.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.74.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.74.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.74.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.74.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.74.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.75.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.75.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.75.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.75.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.75.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.75.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.76.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.76.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.76.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.76.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.76.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.76.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.77.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.77.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.77.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.77.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.77.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.77.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.78.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.78.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.78.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.78.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.78.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.78.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.79.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.79.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.79.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.79.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.79.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.79.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.8.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.8.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.8.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.8.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.8.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.8.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.80.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.80.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.80.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.80.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.80.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.80.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.81.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.81.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.81.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.81.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.81.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.81.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.82.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.82.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.82.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.82.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.82.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.82.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.83.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.83.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.83.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.83.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.83.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.83.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.84.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.84.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.84.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.84.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.84.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.84.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.85.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.85.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.85.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.85.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.85.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.85.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.86.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.86.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.86.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.86.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.86.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.86.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.87.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.87.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.87.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.87.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.87.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.87.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.88.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.88.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.88.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.88.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.88.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.88.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.89.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.89.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.89.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.89.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.89.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.89.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.9.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.9.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.9.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.9.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.9.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.9.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.90.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.90.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.90.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.90.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.90.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.90.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.91.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.91.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.91.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.91.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.91.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.91.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.92.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.92.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.92.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.92.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.92.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.92.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.93.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.93.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.93.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.93.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.93.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.93.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.94.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.94.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.94.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.94.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.94.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.94.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.95.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.95.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.95.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.95.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.95.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.95.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.96.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.96.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.96.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.96.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.96.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.96.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.97.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.97.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.97.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.97.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.97.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.97.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.98.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.98.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.98.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.98.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.98.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.98.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.99.w1.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.99.w1.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.99.w2.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.99.w2.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.99.w3.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.experts.99.w3.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.shared_experts.down_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.shared_experts.gate_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.shared_experts.up_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.input_layernorm.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.post_attention_layernorm.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.index_k_norm.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.index_k_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.index_q_norm.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.index_q_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.k_norm.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.k_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.k_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.o_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.o_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.q_norm.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.q_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.q_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.v_proj.weight": "model-00047-of-00059.safetensors", - "language_model.model.layers.47.self_attn.v_proj.weight_scale": "model-00047-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.e_score_correction_bias": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.e_score_correction_bias": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.0.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.0.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.0.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.1.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.1.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.1.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.10.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.10.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.10.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.100.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.100.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.100.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.101.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.101.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.101.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.102.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.102.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.102.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.103.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.103.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.103.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.104.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.104.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.104.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.105.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.105.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.105.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.106.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.106.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.106.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.107.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.107.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.41.block_sparse_moe.experts.107.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.0.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.0.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.0.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.1.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.1.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.1.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.10.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.10.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.10.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.100.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.100.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.100.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.101.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.101.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.101.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.102.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.102.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.102.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.103.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.103.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.103.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.104.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.104.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.104.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.105.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.105.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.105.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.106.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.106.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.106.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.107.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.107.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.107.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.108.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.108.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.108.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.108.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.108.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.108.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.109.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.109.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.109.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.109.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.109.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.109.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.11.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.11.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.11.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.110.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.110.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.110.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.110.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.110.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.110.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.111.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.111.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.111.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.111.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.111.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.111.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.112.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.112.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.112.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.112.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.112.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.112.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.113.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.113.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.113.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.113.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.113.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.113.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.114.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.114.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.114.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.114.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.114.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.114.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.115.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.115.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.115.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.115.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.115.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.115.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.116.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.116.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.116.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.116.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.116.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.116.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.117.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.117.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.117.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.117.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.117.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.117.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.118.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.118.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.118.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.118.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.118.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.118.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.119.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.119.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.119.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.119.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.119.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.119.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.12.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.12.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.12.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.120.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.120.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.120.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.120.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.120.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.120.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.121.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.121.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.121.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.121.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.121.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.121.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.122.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.122.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.122.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.122.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.122.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.122.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.123.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.123.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.123.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.123.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.123.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.123.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.124.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.124.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.124.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.124.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.124.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.124.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.125.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.125.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.125.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.125.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.125.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.125.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.126.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.126.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.126.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.126.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.126.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.126.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.127.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.127.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.127.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.127.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.127.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.127.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.13.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.13.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.13.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.14.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.14.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.14.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.15.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.15.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.15.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.16.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.16.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.16.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.17.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.17.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.17.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.18.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.18.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.18.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.19.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.19.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.19.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.2.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.2.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.2.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.20.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.20.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.20.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.21.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.21.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.21.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.22.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.22.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.22.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.23.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.23.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.23.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.24.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.24.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.24.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.25.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.25.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.25.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.26.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.26.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.26.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.27.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.27.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.27.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.28.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.28.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.28.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.29.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.29.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.29.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.3.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.3.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.3.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.30.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.30.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.30.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.31.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.31.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.31.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.32.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.32.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.32.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.32.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.32.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.33.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.33.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.33.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.34.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.34.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.34.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.35.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.35.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.35.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.36.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.36.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.36.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.37.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.37.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.37.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.37.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.38.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.38.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.38.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.38.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.39.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.39.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.39.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.39.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.4.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.4.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.4.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.40.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.40.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.40.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.41.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.41.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.41.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.42.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.42.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.42.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.43.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.43.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.43.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.44.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.44.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.44.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.44.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.45.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.45.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.45.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.46.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.46.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.46.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.47.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.47.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.47.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.48.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.48.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.48.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.48.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.49.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.49.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.49.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.49.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.5.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.5.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.5.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.50.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.50.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.50.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.51.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.51.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.51.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.52.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.52.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.52.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.52.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.53.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.53.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.53.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.53.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.53.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.53.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.54.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.54.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.54.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.54.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.54.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.55.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.55.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.55.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.55.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.55.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.56.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.56.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.56.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.56.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.56.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.56.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.57.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.57.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.57.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.57.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.58.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.58.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.58.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.59.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.59.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.59.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.59.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.59.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.59.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.6.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.6.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.6.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.60.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.60.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.60.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.60.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.61.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.61.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.61.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.61.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.62.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.62.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.62.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.62.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.62.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.63.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.63.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.63.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.63.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.63.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.64.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.64.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.64.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.64.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.64.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.64.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.65.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.65.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.65.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.65.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.65.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.65.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.66.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.66.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.66.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.66.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.66.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.66.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.67.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.67.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.67.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.67.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.67.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.67.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.68.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.68.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.68.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.68.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.68.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.68.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.69.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.69.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.69.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.69.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.69.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.69.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.7.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.7.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.7.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.70.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.70.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.70.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.70.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.70.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.70.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.71.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.71.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.71.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.71.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.71.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.71.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.72.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.72.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.72.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.72.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.72.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.72.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.73.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.73.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.73.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.73.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.73.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.73.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.74.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.74.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.74.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.74.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.74.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.74.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.75.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.75.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.75.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.75.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.75.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.75.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.76.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.76.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.76.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.76.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.76.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.76.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.77.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.77.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.77.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.77.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.77.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.77.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.78.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.78.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.78.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.78.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.78.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.78.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.79.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.79.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.79.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.79.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.79.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.79.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.8.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.8.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.8.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.80.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.80.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.80.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.80.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.80.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.80.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.81.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.81.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.81.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.81.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.81.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.81.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.82.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.82.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.82.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.82.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.82.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.82.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.83.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.83.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.83.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.83.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.83.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.83.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.84.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.84.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.84.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.84.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.84.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.84.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.85.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.85.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.85.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.85.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.85.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.85.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.86.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.86.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.86.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.86.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.86.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.86.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.87.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.87.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.87.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.87.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.87.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.87.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.88.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.88.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.88.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.88.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.88.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.88.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.89.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.89.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.89.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.89.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.89.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.89.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.9.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.9.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.9.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.90.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.90.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.90.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.90.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.90.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.90.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.91.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.91.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.91.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.91.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.91.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.91.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.92.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.92.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.92.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.92.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.92.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.92.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.93.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.93.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.93.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.93.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.93.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.93.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.94.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.94.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.94.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.94.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.94.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.94.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.95.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.95.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.95.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.95.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.95.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.95.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.96.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.96.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.96.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.96.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.96.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.96.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.97.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.97.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.97.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.97.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.97.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.97.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.98.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.98.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.98.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.98.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.98.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.98.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.99.w1.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.99.w1.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.99.w2.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.99.w2.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.99.w3.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.experts.99.w3.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.shared_experts.down_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.shared_experts.gate_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.shared_experts.up_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.input_layernorm.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.post_attention_layernorm.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.index_k_norm.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.index_k_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.index_q_norm.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.index_q_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.k_norm.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.k_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.k_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.o_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.o_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.q_norm.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.q_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.q_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.v_proj.weight": "model-00007-of-00059.safetensors", - "language_model.model.layers.7.self_attn.v_proj.weight_scale": "model-00007-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.gate.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.108.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.108.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.108.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.108.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.108.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.108.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.109.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.109.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.109.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.109.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.109.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.109.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.11.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.11.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.11.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.11.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.11.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.11.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.110.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.110.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.110.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.110.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.110.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.110.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.111.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.111.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.111.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.111.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.111.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.111.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.112.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.112.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.112.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.112.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.112.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.112.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.113.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.113.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.113.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.113.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.113.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.113.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.114.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.114.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.114.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.114.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.114.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.114.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.115.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.115.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.115.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.115.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.115.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.115.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.116.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.116.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.116.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.116.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.116.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.116.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.117.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.117.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.117.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.117.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.117.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.117.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.118.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.118.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.118.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.118.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.118.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.118.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.119.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.119.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.119.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.119.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.119.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.119.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.12.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.12.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.12.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.12.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.12.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.12.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.120.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.120.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.120.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.120.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.120.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.120.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.121.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.121.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.121.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.121.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.121.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.121.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.122.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.122.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.122.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.122.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.122.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.122.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.123.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.123.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.123.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.123.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.123.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.123.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.124.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.124.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.124.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.124.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.124.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.124.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.125.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.125.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.125.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.125.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.125.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.125.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.126.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.126.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.126.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.126.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.126.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.126.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.127.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.127.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.127.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.127.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.127.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.127.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.13.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.13.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.13.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.13.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.13.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.13.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.14.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.14.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.14.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.14.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.14.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.14.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.15.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.15.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.15.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.15.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.15.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.15.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.16.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.16.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.16.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.16.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.16.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.16.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.17.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.17.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.17.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.17.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.17.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.17.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.18.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.18.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.18.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.18.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.18.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.18.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.19.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.19.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.19.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.19.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.19.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.19.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.2.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.2.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.2.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.20.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.20.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.20.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.20.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.20.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.20.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.21.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.21.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.21.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.21.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.21.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.21.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.22.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.22.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.22.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.22.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.22.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.22.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.23.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.23.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.23.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.23.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.23.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.23.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.24.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.24.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.24.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.24.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.24.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.24.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.25.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.25.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.25.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.25.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.25.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.25.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.26.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.26.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.26.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.26.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.26.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.26.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.27.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.27.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.27.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.27.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.27.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.27.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.28.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.28.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.28.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.28.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.28.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.28.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.29.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.29.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.29.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.29.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.29.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.29.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.3.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.3.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.3.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.30.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.30.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.30.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.30.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.30.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.30.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.31.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.31.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.31.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.31.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.31.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.31.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.32.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.32.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.32.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.32.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.32.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.32.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.33.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.33.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.33.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.33.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.33.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.33.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.34.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.34.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.34.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.34.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.34.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.34.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.35.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.35.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.35.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.35.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.35.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.35.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.36.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.36.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.36.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.36.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.36.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.36.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.37.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.37.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.37.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.37.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.37.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.37.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.38.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.38.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.38.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.38.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.38.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.38.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.39.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.39.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.39.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.39.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.39.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.39.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.4.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.4.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.4.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.40.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.40.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.40.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.40.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.40.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.40.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.41.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.41.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.41.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.41.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.41.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.41.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.42.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.42.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.42.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.42.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.42.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.42.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.43.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.43.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.43.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.43.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.43.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.43.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.44.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.44.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.44.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.44.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.44.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.44.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.45.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.45.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.45.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.45.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.45.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.45.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.46.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.46.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.46.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.46.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.46.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.46.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.47.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.47.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.47.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.47.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.47.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.47.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.48.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.48.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.48.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.48.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.48.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.48.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.49.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.49.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.49.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.49.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.49.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.49.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.5.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.5.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.5.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.50.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.50.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.50.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.50.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.50.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.50.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.51.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.51.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.51.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.51.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.51.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.51.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.52.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.52.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.52.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.52.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.52.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.52.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.53.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.53.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.53.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.53.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.53.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.53.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.54.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.54.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.54.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.54.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.54.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.54.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.55.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.55.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.55.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.55.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.55.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.55.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.56.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.56.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.56.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.56.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.56.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.56.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.57.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.57.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.57.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.57.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.57.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.57.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.58.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.58.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.58.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.58.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.58.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.58.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.59.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.59.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.59.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.59.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.59.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.59.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.6.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.6.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.6.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.60.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.60.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.60.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.60.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.60.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.60.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.61.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.61.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.61.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.61.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.61.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.61.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.62.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.62.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.62.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.62.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.62.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.62.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.63.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.63.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.63.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.63.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.63.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.63.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.64.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.64.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.64.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.64.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.64.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.64.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.65.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.65.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.65.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.65.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.65.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.65.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.66.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.66.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.66.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.66.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.66.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.66.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.67.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.67.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.67.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.67.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.67.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.67.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.68.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.68.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.68.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.68.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.68.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.68.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.69.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.69.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.69.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.69.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.69.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.69.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.7.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.7.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.7.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.70.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.70.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.70.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.70.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.70.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.70.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.71.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.71.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.71.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.71.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.71.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.71.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.72.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.72.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.72.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.72.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.72.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.72.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.73.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.73.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.73.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.73.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.73.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.73.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.74.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.74.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.74.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.74.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.74.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.74.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.75.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.75.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.75.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.75.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.75.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.75.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.76.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.76.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.76.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.76.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.76.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.76.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.77.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.77.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.77.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.77.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.77.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.77.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.78.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.78.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.78.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.78.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.78.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.78.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.79.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.79.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.79.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.79.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.79.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.79.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.8.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.8.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.8.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.8.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.8.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.8.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.80.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.80.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.80.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.80.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.80.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.80.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.81.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.81.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.81.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.81.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.81.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.81.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.82.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.82.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.82.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.82.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.82.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.82.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.83.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.83.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.83.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.83.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.83.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.83.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.84.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.84.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.84.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.84.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.84.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.84.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.85.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.85.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.85.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.85.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.85.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.85.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.86.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.86.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.86.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.86.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.86.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.86.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.87.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.87.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.87.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.87.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.87.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.87.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.88.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.88.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.88.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.88.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.88.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.88.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.89.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.89.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.89.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.89.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.89.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.89.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.9.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.9.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.9.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.9.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.9.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.9.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.90.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.90.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.90.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.90.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.90.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.90.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.91.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.91.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.91.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.91.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.91.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.91.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.92.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.92.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.92.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.92.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.92.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.92.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.93.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.93.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.93.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.93.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.93.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.93.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.94.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.94.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.94.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.94.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.94.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.94.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.95.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.95.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.95.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.95.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.95.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.95.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.96.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.96.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.96.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.96.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.96.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.96.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.97.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.97.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.97.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.97.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.97.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.97.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.98.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.98.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.98.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.98.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.98.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.98.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.99.w1.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.99.w1.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.99.w2.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.99.w2.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.99.w3.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.99.w3.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.shared_experts.down_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.shared_experts.gate_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.shared_experts.up_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.input_layernorm.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.post_attention_layernorm.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.index_k_norm.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.index_k_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.index_q_norm.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.index_q_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.k_norm.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.k_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.k_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.o_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.o_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.q_norm.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.q_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.q_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.v_proj.weight": "model-00038-of-00059.safetensors", - "language_model.model.layers.38.self_attn.v_proj.weight_scale": "model-00038-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.gate.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.108.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.108.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.108.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.108.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.108.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.108.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.109.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.109.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.109.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.109.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.109.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.109.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.11.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.11.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.11.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.11.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.11.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.11.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.110.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.110.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.110.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.110.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.110.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.110.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.111.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.111.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.111.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.111.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.111.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.111.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.112.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.112.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.112.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.112.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.112.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.112.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.113.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.113.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.113.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.113.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.113.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.113.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.114.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.114.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.114.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.114.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.114.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.114.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.115.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.115.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.115.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.115.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.115.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.115.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.116.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.116.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.116.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.116.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.116.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.116.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.117.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.117.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.117.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.117.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.117.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.117.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.118.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.118.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.118.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.118.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.118.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.118.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.119.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.119.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.119.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.119.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.119.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.119.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.12.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.12.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.12.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.12.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.12.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.12.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.120.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.120.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.120.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.120.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.120.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.120.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.121.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.121.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.121.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.121.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.121.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.121.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.122.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.122.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.122.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.122.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.122.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.122.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.123.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.123.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.123.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.123.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.123.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.123.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.124.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.124.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.124.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.124.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.124.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.124.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.125.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.125.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.125.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.125.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.125.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.125.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.126.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.126.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.126.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.126.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.126.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.126.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.127.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.127.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.127.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.127.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.127.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.127.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.13.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.13.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.13.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.13.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.13.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.13.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.14.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.14.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.14.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.14.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.14.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.14.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.15.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.15.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.15.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.15.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.15.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.15.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.16.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.16.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.16.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.16.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.16.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.16.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.17.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.17.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.17.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.17.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.17.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.17.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.18.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.18.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.18.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.18.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.18.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.18.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.19.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.19.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.19.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.19.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.19.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.19.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.2.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.2.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.2.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.20.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.20.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.20.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.20.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.20.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.20.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.21.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.21.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.21.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.21.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.21.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.21.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.22.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.22.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.22.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.22.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.22.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.22.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.23.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.23.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.23.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.23.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.23.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.23.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.24.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.24.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.24.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.24.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.24.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.24.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.25.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.25.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.25.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.25.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.25.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.25.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.26.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.26.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.26.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.26.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.26.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.26.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.27.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.27.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.27.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.27.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.27.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.27.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.28.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.28.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.28.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.28.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.28.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.28.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.29.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.29.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.29.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.29.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.29.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.29.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.3.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.3.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.3.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.3.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.3.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.3.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.30.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.30.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.30.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.30.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.30.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.30.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.31.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.31.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.31.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.31.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.31.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.31.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.32.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.32.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.32.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.32.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.32.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.32.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.33.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.33.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.33.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.33.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.33.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.33.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.34.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.34.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.34.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.34.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.34.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.34.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.35.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.35.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.35.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.35.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.35.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.35.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.36.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.36.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.36.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.36.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.36.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.36.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.37.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.37.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.37.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.37.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.37.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.37.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.38.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.38.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.38.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.38.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.38.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.38.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.39.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.39.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.39.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.39.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.39.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.39.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.4.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.4.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.4.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.4.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.4.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.4.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.40.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.40.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.40.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.40.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.40.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.40.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.41.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.41.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.41.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.41.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.41.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.41.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.42.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.42.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.42.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.42.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.42.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.42.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.43.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.43.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.43.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.43.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.43.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.43.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.44.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.44.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.44.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.44.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.44.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.44.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.45.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.45.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.45.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.45.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.45.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.45.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.46.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.46.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.46.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.46.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.46.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.46.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.47.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.47.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.47.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.47.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.47.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.47.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.48.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.48.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.48.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.48.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.48.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.48.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.49.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.49.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.49.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.49.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.49.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.49.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.5.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.5.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.5.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.5.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.5.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.5.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.50.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.50.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.50.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.50.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.50.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.50.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.51.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.51.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.51.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.51.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.51.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.51.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.52.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.52.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.52.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.52.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.52.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.52.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.53.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.53.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.53.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.53.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.53.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.53.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.54.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.54.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.54.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.54.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.54.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.54.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.55.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.55.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.55.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.55.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.55.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.55.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.56.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.56.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.56.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.56.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.56.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.56.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.57.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.57.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.57.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.57.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.57.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.57.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.58.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.58.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.58.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.58.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.58.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.58.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.59.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.59.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.59.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.59.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.59.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.59.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.6.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.6.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.6.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.6.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.6.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.6.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.60.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.60.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.60.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.60.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.60.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.60.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.61.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.61.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.61.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.61.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.61.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.61.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.62.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.62.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.62.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.62.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.62.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.62.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.63.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.63.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.63.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.63.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.63.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.63.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.64.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.64.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.64.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.64.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.64.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.64.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.65.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.65.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.65.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.65.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.65.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.65.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.66.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.66.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.66.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.66.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.66.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.66.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.67.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.67.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.67.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.67.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.67.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.67.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.68.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.68.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.68.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.68.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.68.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.68.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.69.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.69.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.69.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.69.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.69.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.69.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.7.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.7.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.7.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.7.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.7.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.7.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.70.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.70.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.70.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.70.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.70.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.70.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.71.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.71.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.71.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.71.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.71.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.71.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.72.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.72.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.72.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.72.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.72.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.72.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.73.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.73.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.73.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.73.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.73.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.73.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.74.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.74.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.74.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.74.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.74.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.74.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.75.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.75.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.75.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.75.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.75.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.75.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.76.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.76.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.76.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.76.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.76.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.76.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.77.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.77.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.77.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.77.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.77.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.77.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.78.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.78.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.78.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.78.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.78.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.78.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.79.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.79.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.79.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.79.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.79.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.79.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.8.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.8.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.8.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.8.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.8.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.8.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.80.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.80.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.80.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.80.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.80.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.80.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.81.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.81.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.81.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.81.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.81.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.81.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.82.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.82.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.82.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.82.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.82.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.82.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.83.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.83.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.83.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.83.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.83.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.83.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.84.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.84.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.84.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.84.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.84.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.84.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.85.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.85.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.85.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.85.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.85.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.85.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.86.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.86.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.86.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.86.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.86.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.86.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.87.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.87.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.87.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.87.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.87.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.87.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.88.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.88.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.88.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.88.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.88.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.88.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.89.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.89.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.89.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.89.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.89.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.89.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.9.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.9.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.9.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.9.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.9.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.9.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.90.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.90.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.90.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.90.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.90.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.90.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.91.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.91.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.91.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.91.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.91.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.91.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.92.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.92.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.92.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.92.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.92.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.92.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.93.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.93.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.93.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.93.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.93.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.93.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.94.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.94.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.94.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.94.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.94.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.94.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.95.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.95.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.95.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.95.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.95.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.95.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.96.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.96.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.96.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.96.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.96.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.96.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.97.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.97.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.97.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.97.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.97.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.97.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.98.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.98.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.98.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.98.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.98.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.98.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.99.w1.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.99.w1.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.99.w2.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.99.w2.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.99.w3.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.experts.99.w3.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.shared_experts.down_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.shared_experts.gate_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.shared_experts.up_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.input_layernorm.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.post_attention_layernorm.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.index_k_norm.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.index_k_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.index_q_norm.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.index_q_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.k_norm.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.k_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.k_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.o_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.o_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.q_norm.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.q_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.q_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.v_proj.weight": "model-00053-of-00059.safetensors", - "language_model.model.layers.53.self_attn.v_proj.weight_scale": "model-00053-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.gate.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.108.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.108.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.108.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.108.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.108.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.108.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.109.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.109.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.109.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.109.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.109.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.109.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.11.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.11.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.11.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.11.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.11.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.11.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.110.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.110.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.110.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.110.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.110.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.110.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.111.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.111.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.111.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.111.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.111.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.111.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.112.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.112.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.112.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.112.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.112.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.112.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.113.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.113.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.113.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.113.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.113.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.113.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.114.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.114.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.114.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.114.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.114.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.114.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.115.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.115.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.115.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.115.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.115.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.115.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.116.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.116.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.116.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.116.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.116.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.116.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.117.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.117.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.117.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.117.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.117.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.117.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.118.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.118.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.118.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.118.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.118.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.118.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.119.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.119.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.119.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.119.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.119.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.119.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.12.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.12.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.12.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.12.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.12.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.12.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.120.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.120.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.120.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.120.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.120.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.120.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.121.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.121.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.121.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.121.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.121.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.121.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.122.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.122.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.122.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.122.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.122.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.122.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.123.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.123.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.123.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.123.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.123.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.123.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.124.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.124.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.124.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.124.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.124.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.124.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.125.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.125.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.125.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.125.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.125.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.125.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.126.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.126.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.126.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.126.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.126.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.126.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.127.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.127.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.127.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.127.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.127.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.127.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.13.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.13.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.13.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.13.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.13.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.13.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.14.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.14.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.14.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.14.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.14.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.14.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.15.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.15.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.15.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.15.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.15.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.15.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.16.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.16.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.16.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.16.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.16.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.16.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.17.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.17.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.17.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.17.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.17.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.17.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.18.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.18.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.18.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.18.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.18.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.18.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.19.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.19.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.19.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.19.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.19.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.19.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.2.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.2.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.2.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.2.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.2.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.2.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.20.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.20.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.20.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.20.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.20.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.20.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.21.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.21.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.21.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.21.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.21.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.21.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.22.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.22.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.22.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.22.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.22.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.22.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.23.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.23.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.23.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.23.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.23.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.23.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.24.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.24.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.24.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.24.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.24.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.24.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.25.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.25.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.25.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.25.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.25.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.25.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.26.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.26.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.26.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.26.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.26.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.26.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.27.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.27.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.27.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.27.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.27.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.27.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.28.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.28.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.28.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.28.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.28.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.28.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.29.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.29.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.29.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.29.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.29.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.29.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.3.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.3.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.3.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.3.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.3.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.3.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.30.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.30.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.30.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.30.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.30.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.30.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.31.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.31.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.31.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.31.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.31.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.31.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.32.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.32.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.32.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.32.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.32.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.32.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.33.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.33.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.33.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.33.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.33.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.33.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.34.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.34.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.34.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.34.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.34.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.34.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.35.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.35.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.35.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.35.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.35.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.35.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.36.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.36.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.36.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.36.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.36.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.36.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.37.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.37.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.37.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.37.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.37.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.37.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.38.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.38.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.38.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.38.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.38.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.38.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.39.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.39.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.39.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.39.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.39.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.39.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.4.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.4.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.4.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.4.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.4.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.4.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.40.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.40.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.40.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.40.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.40.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.40.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.41.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.41.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.41.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.41.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.41.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.41.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.42.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.42.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.42.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.42.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.42.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.42.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.43.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.43.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.43.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.43.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.43.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.43.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.44.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.44.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.44.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.44.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.44.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.44.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.45.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.45.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.45.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.45.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.45.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.45.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.46.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.46.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.46.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.46.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.46.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.46.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.47.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.47.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.47.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.47.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.47.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.47.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.48.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.48.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.48.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.48.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.48.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.48.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.49.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.49.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.49.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.49.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.49.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.49.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.5.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.5.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.5.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.5.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.5.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.5.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.50.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.50.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.50.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.50.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.50.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.50.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.51.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.51.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.51.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.51.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.51.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.51.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.52.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.52.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.52.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.52.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.52.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.52.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.53.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.53.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.53.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.53.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.53.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.53.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.54.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.54.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.54.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.54.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.54.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.54.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.55.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.55.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.55.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.55.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.55.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.55.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.56.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.56.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.56.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.56.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.56.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.56.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.57.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.57.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.57.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.57.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.57.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.57.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.58.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.58.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.58.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.58.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.58.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.58.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.59.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.59.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.59.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.59.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.59.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.59.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.6.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.6.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.6.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.6.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.6.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.6.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.60.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.60.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.60.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.60.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.60.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.60.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.61.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.61.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.61.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.61.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.61.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.61.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.62.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.62.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.62.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.62.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.62.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.62.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.63.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.63.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.63.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.63.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.63.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.63.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.64.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.64.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.64.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.64.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.64.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.64.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.65.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.65.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.65.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.65.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.65.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.65.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.66.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.66.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.66.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.66.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.66.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.66.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.67.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.67.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.67.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.67.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.67.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.67.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.68.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.68.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.68.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.68.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.68.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.68.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.69.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.69.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.69.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.69.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.69.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.69.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.7.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.7.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.7.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.7.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.7.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.7.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.70.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.70.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.70.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.70.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.70.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.70.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.71.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.71.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.71.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.71.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.71.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.71.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.72.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.72.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.72.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.72.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.72.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.72.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.73.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.73.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.73.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.73.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.73.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.73.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.74.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.74.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.74.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.74.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.74.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.74.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.75.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.75.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.75.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.75.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.75.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.75.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.76.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.76.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.76.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.76.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.76.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.76.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.77.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.77.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.77.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.77.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.77.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.77.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.78.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.78.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.78.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.78.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.78.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.78.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.79.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.79.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.79.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.79.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.79.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.79.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.8.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.8.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.8.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.8.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.8.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.8.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.80.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.80.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.80.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.80.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.80.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.80.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.81.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.81.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.81.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.81.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.81.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.81.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.82.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.82.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.82.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.82.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.82.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.82.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.83.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.83.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.83.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.83.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.83.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.83.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.84.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.84.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.84.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.84.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.84.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.84.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.85.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.85.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.85.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.85.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.85.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.85.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.86.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.86.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.86.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.86.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.86.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.86.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.87.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.87.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.87.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.87.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.87.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.87.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.88.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.88.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.88.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.88.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.88.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.88.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.89.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.89.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.89.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.89.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.89.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.89.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.9.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.9.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.9.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.9.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.9.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.9.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.90.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.90.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.90.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.90.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.90.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.90.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.91.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.91.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.91.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.91.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.91.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.91.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.92.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.92.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.92.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.92.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.92.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.92.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.93.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.93.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.93.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.93.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.93.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.93.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.94.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.94.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.94.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.94.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.94.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.94.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.95.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.95.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.95.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.95.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.95.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.95.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.96.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.96.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.96.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.96.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.96.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.96.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.97.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.97.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.97.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.97.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.97.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.97.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.98.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.98.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.98.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.98.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.98.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.98.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.99.w1.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.99.w1.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.99.w2.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.99.w2.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.99.w3.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.99.w3.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.shared_experts.down_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.shared_experts.gate_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.shared_experts.up_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.input_layernorm.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.post_attention_layernorm.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.index_k_norm.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.index_k_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.index_q_norm.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.index_q_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.k_norm.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.k_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.k_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.o_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.o_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.q_norm.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.q_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.q_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.v_proj.weight": "model-00058-of-00059.safetensors", - "language_model.model.layers.58.self_attn.v_proj.weight_scale": "model-00058-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.gate.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.108.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.108.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.108.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.108.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.108.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.108.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.109.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.109.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.109.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.109.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.109.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.109.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.11.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.11.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.11.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.11.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.11.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.11.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.110.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.110.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.110.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.110.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.110.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.110.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.111.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.111.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.111.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.111.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.111.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.111.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.112.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.112.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.112.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.112.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.112.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.112.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.113.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.113.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.113.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.113.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.113.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.113.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.114.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.114.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.114.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.114.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.114.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.114.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.115.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.115.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.115.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.115.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.115.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.115.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.116.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.116.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.116.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.116.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.116.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.116.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.117.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.117.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.117.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.117.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.117.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.117.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.118.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.118.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.118.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.118.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.118.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.118.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.119.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.119.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.119.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.119.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.119.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.119.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.12.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.12.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.12.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.12.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.12.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.12.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.120.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.120.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.120.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.120.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.120.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.120.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.121.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.121.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.121.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.121.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.121.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.121.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.122.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.122.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.122.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.122.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.122.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.122.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.123.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.123.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.123.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.123.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.123.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.123.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.124.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.124.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.124.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.124.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.124.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.124.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.125.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.125.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.125.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.125.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.125.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.125.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.126.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.126.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.126.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.126.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.126.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.126.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.127.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.127.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.127.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.127.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.127.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.127.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.13.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.13.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.13.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.13.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.13.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.13.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.14.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.14.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.14.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.14.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.14.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.14.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.15.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.15.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.15.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.15.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.15.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.15.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.16.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.16.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.16.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.16.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.16.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.16.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.17.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.17.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.17.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.17.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.17.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.17.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.18.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.18.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.18.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.18.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.18.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.18.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.19.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.19.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.19.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.19.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.19.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.19.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.2.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.2.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.2.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.20.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.20.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.20.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.20.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.20.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.20.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.21.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.21.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.21.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.21.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.21.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.21.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.22.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.22.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.22.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.22.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.22.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.22.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.23.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.23.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.23.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.23.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.23.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.23.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.24.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.24.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.24.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.24.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.24.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.24.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.25.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.25.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.25.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.25.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.25.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.25.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.26.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.26.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.26.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.26.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.26.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.26.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.27.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.27.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.27.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.27.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.27.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.27.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.28.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.28.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.28.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.28.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.28.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.28.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.29.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.29.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.29.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.29.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.29.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.29.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.3.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.3.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.3.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.30.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.30.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.30.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.30.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.30.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.30.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.31.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.31.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.31.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.31.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.31.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.31.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.32.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.32.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.32.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.32.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.32.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.32.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.33.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.33.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.33.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.33.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.33.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.33.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.34.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.34.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.34.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.34.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.34.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.34.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.35.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.35.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.35.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.35.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.35.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.35.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.36.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.36.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.36.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.36.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.36.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.36.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.37.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.37.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.37.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.37.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.37.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.37.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.38.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.38.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.38.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.38.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.38.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.38.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.39.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.39.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.39.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.39.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.39.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.39.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.4.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.4.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.4.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.4.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.4.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.4.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.40.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.40.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.40.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.40.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.40.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.40.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.41.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.41.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.41.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.41.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.41.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.41.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.42.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.42.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.42.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.42.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.42.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.42.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.43.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.43.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.43.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.43.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.43.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.43.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.44.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.44.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.44.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.44.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.44.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.44.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.45.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.45.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.45.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.45.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.45.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.45.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.46.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.46.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.46.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.46.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.46.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.46.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.47.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.47.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.47.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.47.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.47.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.47.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.48.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.48.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.48.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.48.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.48.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.48.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.49.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.49.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.49.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.49.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.49.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.49.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.5.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.5.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.5.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.5.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.5.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.5.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.50.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.50.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.50.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.50.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.50.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.50.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.51.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.51.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.51.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.51.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.51.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.51.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.52.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.52.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.52.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.52.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.52.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.52.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.53.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.53.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.53.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.53.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.53.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.53.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.54.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.54.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.54.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.54.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.54.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.54.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.55.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.55.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.55.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.55.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.55.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.55.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.56.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.56.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.56.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.56.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.56.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.56.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.57.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.57.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.57.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.57.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.57.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.57.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.58.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.58.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.58.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.58.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.58.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.58.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.59.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.59.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.59.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.59.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.59.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.59.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.6.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.6.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.6.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.6.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.6.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.6.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.60.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.60.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.60.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.60.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.60.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.60.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.61.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.61.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.61.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.61.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.61.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.61.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.62.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.62.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.62.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.62.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.62.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.62.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.63.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.63.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.63.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.63.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.63.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.63.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.64.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.64.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.64.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.64.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.64.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.64.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.65.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.65.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.65.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.65.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.65.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.65.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.66.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.66.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.66.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.66.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.66.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.66.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.67.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.67.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.67.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.67.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.67.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.67.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.68.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.68.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.68.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.68.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.68.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.68.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.69.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.69.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.69.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.69.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.69.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.69.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.7.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.7.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.7.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.7.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.70.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.70.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.70.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.70.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.70.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.70.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.71.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.71.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.71.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.71.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.71.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.71.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.72.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.72.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.72.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.72.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.72.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.72.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.73.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.73.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.73.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.73.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.73.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.73.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.74.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.74.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.74.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.74.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.74.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.74.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.75.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.75.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.75.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.75.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.75.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.75.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.76.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.76.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.76.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.76.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.76.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.76.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.77.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.77.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.77.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.77.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.77.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.77.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.78.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.78.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.78.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.78.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.78.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.78.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.79.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.79.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.79.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.79.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.79.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.79.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.8.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.8.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.8.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.8.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.8.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.8.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.80.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.80.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.80.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.80.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.80.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.80.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.81.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.81.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.81.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.81.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.81.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.81.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.82.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.82.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.82.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.82.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.82.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.82.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.83.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.83.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.83.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.83.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.83.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.83.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.84.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.84.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.84.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.84.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.84.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.84.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.85.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.85.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.85.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.85.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.85.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.85.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.86.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.86.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.86.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.86.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.86.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.86.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.87.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.87.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.87.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.87.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.87.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.87.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.88.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.88.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.88.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.88.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.88.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.88.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.89.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.89.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.89.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.89.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.89.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.89.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.9.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.9.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.9.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.9.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.9.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.9.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.90.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.90.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.90.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.90.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.90.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.90.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.91.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.91.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.91.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.91.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.91.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.91.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.92.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.92.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.92.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.92.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.92.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.92.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.93.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.93.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.93.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.93.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.93.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.93.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.94.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.94.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.94.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.94.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.94.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.94.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.95.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.95.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.95.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.95.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.95.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.95.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.96.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.96.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.96.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.96.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.96.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.96.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.97.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.97.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.97.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.97.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.97.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.97.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.98.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.98.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.98.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.98.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.98.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.98.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.99.w1.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.99.w1.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.99.w2.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.99.w2.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.99.w3.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.experts.99.w3.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.shared_experts.down_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.shared_experts.gate_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.shared_experts.up_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.input_layernorm.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.post_attention_layernorm.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.index_k_norm.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.index_k_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.index_q_norm.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.index_q_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.k_norm.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.k_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.k_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.o_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.o_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.q_norm.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.q_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.q_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.v_proj.weight": "model-00046-of-00059.safetensors", - "language_model.model.layers.46.self_attn.v_proj.weight_scale": "model-00046-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.e_score_correction_bias": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.gate.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.0.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.0.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.0.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.1.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.1.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.1.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.10.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.10.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.10.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.10.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.10.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.10.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.100.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.100.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.100.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.100.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.100.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.100.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.101.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.101.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.101.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.101.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.101.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.101.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.102.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.102.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.102.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.102.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.102.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.102.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.103.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.103.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.103.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.103.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.103.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.103.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.104.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.104.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.104.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.104.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.104.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.104.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.105.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.105.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.105.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.105.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.105.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.105.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.106.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.106.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.106.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.106.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.106.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.106.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.107.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.107.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.107.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.107.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.107.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.107.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.108.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.108.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.108.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.108.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.108.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.108.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.109.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.109.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.109.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.109.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.109.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.109.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.11.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.11.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.11.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.11.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.11.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.11.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.110.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.110.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.110.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.110.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.110.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.110.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.111.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.111.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.111.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.111.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.111.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.111.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.112.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.112.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.112.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.112.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.112.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.112.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.113.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.113.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.113.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.113.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.113.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.113.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.114.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.114.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.114.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.114.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.114.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.114.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.115.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.115.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.115.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.115.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.115.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.115.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.116.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.116.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.116.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.116.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.116.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.116.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.117.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.117.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.117.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.117.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.117.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.117.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.118.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.118.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.118.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.118.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.118.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.118.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.119.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.119.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.119.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.119.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.119.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.119.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.12.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.12.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.12.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.12.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.12.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.12.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.120.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.120.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.120.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.120.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.120.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.120.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.121.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.121.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.121.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.121.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.121.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.121.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.122.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.122.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.122.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.122.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.122.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.122.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.123.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.123.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.123.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.123.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.123.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.123.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.124.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.124.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.124.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.124.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.124.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.124.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.125.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.125.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.125.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.125.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.125.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.125.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.126.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.126.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.126.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.126.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.126.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.126.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.127.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.127.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.127.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.127.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.127.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.127.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.13.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.13.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.13.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.13.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.13.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.13.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.14.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.14.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.14.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.14.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.14.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.14.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.15.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.15.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.15.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.15.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.15.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.15.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.16.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.16.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.16.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.16.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.16.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.16.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.17.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.17.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.17.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.17.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.17.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.17.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.18.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.18.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.18.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.18.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.18.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.18.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.19.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.19.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.19.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.19.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.19.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.19.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.2.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.2.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.2.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.20.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.20.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.20.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.20.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.20.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.20.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.21.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.21.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.21.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.21.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.21.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.21.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.22.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.22.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.22.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.22.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.22.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.22.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.23.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.23.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.23.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.23.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.23.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.23.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.24.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.24.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.24.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.24.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.24.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.24.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.25.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.25.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.25.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.25.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.25.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.25.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.26.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.26.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.26.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.26.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.26.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.26.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.27.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.27.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.27.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.27.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.27.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.27.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.28.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.28.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.28.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.28.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.28.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.28.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.29.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.29.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.29.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.29.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.29.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.29.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.3.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.3.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.3.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.30.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.30.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.30.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.30.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.30.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.30.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.31.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.31.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.31.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.31.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.31.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.31.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.32.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.32.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.32.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.32.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.32.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.32.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.33.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.33.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.33.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.33.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.33.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.33.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.34.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.34.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.34.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.34.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.34.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.34.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.35.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.35.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.35.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.35.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.35.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.35.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.36.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.36.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.36.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.36.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.36.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.36.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.37.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.37.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.37.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.37.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.37.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.37.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.38.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.38.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.38.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.38.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.38.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.38.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.39.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.39.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.39.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.39.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.39.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.39.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.4.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.4.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.4.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.40.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.40.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.40.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.40.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.40.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.40.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.41.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.41.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.41.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.41.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.41.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.41.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.42.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.42.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.42.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.42.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.42.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.42.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.43.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.43.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.43.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.43.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.43.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.43.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.44.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.44.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.44.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.44.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.44.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.44.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.45.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.45.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.45.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.45.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.45.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.45.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.46.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.46.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.46.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.46.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.46.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.46.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.47.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.47.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.47.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.47.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.47.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.47.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.48.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.48.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.48.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.48.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.48.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.48.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.49.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.49.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.49.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.49.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.49.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.49.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.5.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.5.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.5.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.50.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.50.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.50.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.50.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.50.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.50.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.51.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.51.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.51.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.51.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.51.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.51.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.52.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.52.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.52.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.52.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.52.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.52.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.53.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.53.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.53.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.53.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.53.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.53.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.54.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.54.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.54.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.54.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.54.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.54.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.55.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.55.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.55.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.55.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.55.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.55.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.56.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.56.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.56.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.56.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.56.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.56.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.57.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.57.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.57.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.57.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.57.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.57.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.58.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.58.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.58.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.58.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.58.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.58.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.59.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.59.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.59.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.59.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.59.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.59.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.6.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.6.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.6.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.60.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.60.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.60.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.60.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.60.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.60.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.61.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.61.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.61.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.61.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.61.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.61.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.62.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.62.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.62.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.62.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.62.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.62.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.63.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.63.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.63.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.63.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.63.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.63.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.64.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.64.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.64.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.64.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.64.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.64.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.65.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.65.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.65.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.65.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.65.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.65.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.66.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.66.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.66.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.66.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.66.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.66.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.67.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.67.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.67.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.67.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.67.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.67.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.68.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.68.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.68.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.68.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.68.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.68.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.69.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.69.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.69.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.69.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.69.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.69.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.7.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.7.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.7.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.70.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.70.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.70.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.70.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.70.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.70.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.71.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.71.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.71.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.71.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.71.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.71.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.72.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.72.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.72.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.72.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.72.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.72.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.73.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.73.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.73.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.73.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.73.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.73.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.74.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.74.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.74.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.74.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.74.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.74.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.75.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.75.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.75.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.75.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.75.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.75.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.76.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.76.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.76.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.76.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.76.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.76.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.77.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.77.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.77.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.77.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.77.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.77.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.78.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.78.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.78.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.78.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.78.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.78.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.79.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.79.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.79.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.79.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.79.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.79.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.8.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.8.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.8.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.8.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.8.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.8.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.80.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.80.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.80.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.80.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.80.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.80.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.81.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.81.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.81.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.81.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.81.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.81.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.82.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.82.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.82.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.82.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.82.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.82.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.83.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.83.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.83.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.83.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.83.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.83.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.84.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.84.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.84.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.84.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.84.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.84.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.85.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.85.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.85.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.85.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.85.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.85.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.86.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.86.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.86.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.86.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.86.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.86.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.87.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.87.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.87.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.87.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.87.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.87.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.88.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.88.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.88.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.88.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.88.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.88.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.89.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.89.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.89.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.89.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.89.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.89.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.9.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.9.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.9.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.9.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.9.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.9.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.90.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.90.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.90.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.90.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.90.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.90.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.91.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.91.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.91.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.91.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.91.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.91.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.92.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.92.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.92.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.92.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.92.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.92.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.93.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.93.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.93.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.93.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.93.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.93.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.94.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.94.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.94.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.94.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.94.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.94.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.95.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.95.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.95.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.95.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.95.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.95.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.96.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.96.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.96.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.96.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.96.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.96.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.97.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.97.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.97.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.97.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.97.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.97.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.98.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.98.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.98.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.98.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.98.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.98.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.99.w1.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.99.w1.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.99.w2.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.99.w2.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.99.w3.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.experts.99.w3.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.shared_experts.down_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.shared_experts.gate_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.shared_experts.up_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.input_layernorm.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.post_attention_layernorm.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.index_k_norm.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.index_k_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.index_q_norm.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.index_q_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.k_norm.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.k_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.k_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.o_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.o_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.q_norm.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.q_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.q_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.v_proj.weight": "model-00034-of-00059.safetensors", - "language_model.model.layers.34.self_attn.v_proj.weight_scale": "model-00034-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.e_score_correction_bias": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.gate.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.0.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.0.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.0.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.1.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.1.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.1.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.10.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.10.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.10.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.10.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.10.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.10.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.100.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.100.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.100.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.100.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.100.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.100.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.101.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.101.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.101.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.101.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.101.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.101.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.102.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.102.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.102.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.102.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.102.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.102.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.103.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.103.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.103.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.103.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.103.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.103.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.104.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.104.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.104.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.104.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.104.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.104.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.105.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.105.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.105.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.105.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.105.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.105.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.106.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.106.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.106.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.106.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.106.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.106.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.107.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.107.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.107.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.107.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.107.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.107.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.108.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.108.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.108.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.108.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.108.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.108.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.109.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.109.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.109.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.109.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.109.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.109.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.11.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.11.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.11.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.11.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.11.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.11.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.110.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.110.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.110.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.110.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.110.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.110.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.111.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.111.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.111.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.111.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.111.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.111.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.112.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.112.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.112.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.112.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.112.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.112.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.113.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.113.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.113.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.113.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.113.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.113.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.114.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.114.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.114.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.114.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.114.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.114.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.115.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.115.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.115.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.115.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.115.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.115.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.116.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.116.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.116.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.116.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.116.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.116.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.117.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.117.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.117.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.117.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.117.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.117.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.118.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.118.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.118.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.118.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.118.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.118.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.119.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.119.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.119.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.119.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.119.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.119.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.12.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.12.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.12.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.12.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.12.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.12.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.120.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.120.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.120.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.120.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.120.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.120.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.121.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.121.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.121.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.121.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.121.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.121.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.122.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.122.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.122.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.122.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.122.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.122.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.123.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.123.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.123.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.123.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.123.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.123.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.124.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.124.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.124.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.124.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.124.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.124.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.125.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.125.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.125.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.125.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.125.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.125.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.126.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.126.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.126.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.126.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.126.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.126.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.127.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.127.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.127.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.127.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.127.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.127.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.13.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.13.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.13.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.13.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.13.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.13.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.14.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.14.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.14.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.14.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.14.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.14.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.15.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.15.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.15.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.15.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.15.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.15.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.16.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.16.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.16.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.16.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.16.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.16.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.17.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.17.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.17.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.17.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.17.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.17.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.18.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.18.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.18.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.18.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.18.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.18.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.19.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.19.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.19.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.19.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.19.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.19.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.2.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.2.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.2.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.20.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.20.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.20.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.20.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.20.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.20.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.21.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.21.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.21.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.21.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.21.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.21.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.22.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.22.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.22.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.22.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.22.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.22.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.23.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.23.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.23.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.23.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.23.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.23.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.24.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.24.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.24.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.24.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.24.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.24.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.25.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.25.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.25.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.25.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.25.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.25.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.26.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.26.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.26.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.26.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.26.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.26.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.27.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.27.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.27.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.27.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.27.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.27.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.28.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.28.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.28.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.28.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.28.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.28.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.29.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.29.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.29.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.29.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.29.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.29.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.3.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.3.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.3.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.30.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.30.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.30.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.30.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.30.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.30.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.31.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.31.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.31.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.31.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.31.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.31.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.32.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.32.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.32.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.32.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.32.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.32.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.33.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.33.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.33.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.33.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.33.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.33.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.34.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.34.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.34.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.34.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.34.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.34.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.35.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.35.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.35.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.35.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.35.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.35.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.36.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.36.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.36.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.36.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.36.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.36.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.37.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.37.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.37.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.37.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.37.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.37.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.38.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.38.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.38.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.38.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.38.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.38.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.39.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.39.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.39.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.39.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.39.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.39.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.4.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.4.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.4.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.40.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.40.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.40.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.40.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.40.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.40.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.41.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.41.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.41.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.41.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.41.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.41.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.42.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.42.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.42.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.42.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.42.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.42.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.43.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.43.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.43.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.43.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.43.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.43.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.44.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.44.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.44.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.44.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.44.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.44.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.45.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.45.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.45.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.45.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.45.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.45.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.46.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.46.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.46.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.46.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.46.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.46.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.47.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.47.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.47.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.47.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.47.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.47.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.48.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.48.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.48.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.48.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.48.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.48.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.49.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.49.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.49.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.49.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.49.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.49.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.5.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.5.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.5.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.50.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.50.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.50.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.50.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.50.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.50.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.51.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.51.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.51.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.51.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.51.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.51.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.52.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.52.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.52.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.52.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.52.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.52.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.53.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.53.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.53.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.53.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.53.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.53.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.54.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.54.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.54.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.54.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.54.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.54.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.55.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.55.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.55.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.55.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.55.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.55.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.56.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.56.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.56.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.56.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.56.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.56.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.57.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.57.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.57.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.57.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.57.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.57.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.58.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.58.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.58.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.58.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.58.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.58.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.59.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.59.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.59.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.59.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.59.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.59.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.6.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.6.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.6.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.60.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.60.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.60.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.60.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.60.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.60.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.61.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.61.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.61.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.61.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.61.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.61.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.62.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.62.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.62.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.62.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.62.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.62.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.63.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.63.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.63.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.63.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.63.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.63.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.64.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.64.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.64.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.64.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.64.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.64.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.65.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.65.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.65.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.65.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.65.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.65.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.66.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.66.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.66.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.66.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.66.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.66.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.67.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.67.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.67.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.67.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.67.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.67.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.68.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.68.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.68.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.68.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.68.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.68.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.69.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.69.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.69.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.69.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.69.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.69.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.7.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.7.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.7.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.70.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.70.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.70.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.70.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.70.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.70.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.71.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.71.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.71.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.71.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.71.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.71.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.72.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.72.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.72.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.72.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.72.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.72.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.73.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.73.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.73.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.73.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.73.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.73.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.74.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.74.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.74.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.74.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.74.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.74.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.75.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.75.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.75.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.75.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.75.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.75.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.76.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.76.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.76.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.76.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.76.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.76.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.77.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.77.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.77.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.77.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.77.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.77.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.78.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.78.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.78.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.78.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.78.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.78.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.79.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.79.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.79.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.79.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.79.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.79.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.8.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.8.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.8.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.8.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.8.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.8.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.80.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.80.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.80.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.80.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.80.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.80.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.81.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.81.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.81.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.81.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.81.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.81.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.82.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.82.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.82.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.82.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.82.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.82.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.83.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.83.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.83.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.83.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.83.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.83.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.84.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.84.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.84.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.84.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.84.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.84.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.85.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.85.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.85.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.85.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.85.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.85.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.86.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.86.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.86.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.86.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.86.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.86.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.87.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.87.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.87.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.87.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.87.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.87.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.88.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.88.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.88.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.88.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.88.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.88.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.89.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.89.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.89.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.89.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.89.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.89.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.9.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.9.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.9.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.9.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.9.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.9.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.90.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.90.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.90.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.90.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.90.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.90.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.91.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.91.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.91.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.91.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.91.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.91.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.92.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.92.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.92.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.92.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.92.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.92.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.93.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.93.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.93.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.93.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.93.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.93.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.94.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.94.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.94.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.94.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.94.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.94.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.95.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.95.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.95.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.95.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.95.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.95.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.96.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.96.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.96.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.96.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.96.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.96.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.97.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.97.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.97.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.97.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.97.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.97.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.98.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.98.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.98.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.98.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.98.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.98.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.99.w1.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.99.w1.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.99.w2.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.99.w2.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.99.w3.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.experts.99.w3.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.shared_experts.down_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.shared_experts.gate_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.shared_experts.up_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.input_layernorm.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.post_attention_layernorm.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.index_k_norm.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.index_k_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.index_q_norm.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.index_q_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.k_norm.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.k_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.k_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.o_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.o_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.q_norm.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.q_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.q_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.v_proj.weight": "model-00035-of-00059.safetensors", - "language_model.model.layers.35.self_attn.v_proj.weight_scale": "model-00035-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.e_score_correction_bias": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.gate.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.0.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.0.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.0.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.1.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.1.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.1.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.10.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.10.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.10.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.10.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.10.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.10.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.100.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.100.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.100.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.100.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.100.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.100.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.101.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.101.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.101.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.101.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.101.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.101.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.102.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.102.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.102.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.102.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.102.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.102.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.103.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.103.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.103.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.103.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.103.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.103.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.104.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.104.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.104.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.104.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.104.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.104.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.105.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.105.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.105.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.105.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.105.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.105.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.106.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.106.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.106.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.106.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.106.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.106.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.107.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.107.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.107.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.107.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.107.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.107.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.108.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.108.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.108.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.108.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.108.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.108.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.109.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.109.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.109.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.109.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.109.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.109.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.11.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.11.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.11.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.11.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.11.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.11.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.110.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.110.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.110.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.110.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.110.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.110.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.111.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.111.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.111.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.111.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.111.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.111.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.112.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.112.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.112.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.112.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.112.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.112.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.113.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.113.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.113.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.113.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.113.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.113.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.114.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.114.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.114.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.114.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.114.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.114.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.115.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.115.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.115.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.115.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.115.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.115.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.116.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.116.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.116.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.116.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.116.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.116.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.117.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.117.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.117.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.117.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.117.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.117.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.118.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.118.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.118.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.118.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.118.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.118.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.119.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.119.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.119.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.119.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.119.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.119.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.12.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.12.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.12.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.12.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.12.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.12.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.120.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.120.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.120.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.120.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.120.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.120.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.121.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.121.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.121.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.121.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.121.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.121.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.122.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.122.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.122.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.122.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.122.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.122.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.123.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.123.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.123.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.123.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.123.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.123.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.124.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.124.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.124.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.124.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.124.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.124.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.125.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.125.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.125.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.125.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.125.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.125.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.126.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.126.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.126.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.126.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.126.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.126.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.127.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.127.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.127.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.127.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.127.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.127.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.13.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.13.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.13.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.13.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.13.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.13.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.14.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.14.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.14.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.14.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.14.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.14.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.15.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.15.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.15.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.15.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.15.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.15.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.16.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.16.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.16.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.16.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.16.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.16.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.17.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.17.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.17.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.17.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.17.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.17.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.18.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.18.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.18.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.18.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.18.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.18.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.19.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.19.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.19.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.19.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.19.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.19.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.2.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.2.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.2.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.20.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.20.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.20.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.20.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.20.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.20.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.21.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.21.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.21.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.21.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.21.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.21.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.22.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.22.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.22.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.22.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.22.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.22.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.23.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.23.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.23.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.23.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.23.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.23.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.24.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.24.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.24.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.24.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.24.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.24.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.25.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.25.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.25.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.25.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.25.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.25.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.26.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.26.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.26.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.26.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.26.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.26.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.27.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.27.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.27.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.27.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.27.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.27.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.28.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.28.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.28.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.28.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.28.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.28.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.29.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.29.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.29.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.29.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.29.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.29.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.3.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.3.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.3.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.30.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.30.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.30.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.30.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.30.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.30.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.31.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.31.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.31.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.31.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.31.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.31.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.32.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.32.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.32.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.32.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.32.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.32.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.33.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.33.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.33.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.33.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.33.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.33.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.34.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.34.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.34.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.34.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.34.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.34.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.35.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.35.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.35.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.35.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.35.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.35.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.36.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.36.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.36.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.36.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.36.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.36.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.37.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.37.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.37.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.37.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.37.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.37.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.38.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.38.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.38.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.38.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.38.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.38.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.39.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.39.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.39.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.39.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.39.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.39.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.4.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.4.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.4.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.40.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.40.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.40.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.40.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.40.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.40.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.41.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.41.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.41.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.41.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.41.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.41.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.42.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.42.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.42.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.42.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.42.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.42.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.43.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.43.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.43.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.43.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.43.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.43.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.44.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.44.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.44.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.44.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.44.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.44.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.45.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.45.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.45.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.45.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.45.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.45.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.46.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.46.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.46.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.46.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.46.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.46.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.47.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.47.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.47.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.47.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.47.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.47.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.48.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.48.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.48.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.48.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.48.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.48.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.49.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.49.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.49.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.49.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.49.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.49.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.5.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.5.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.5.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.50.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.50.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.50.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.50.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.50.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.50.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.51.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.51.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.51.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.51.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.51.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.51.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.52.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.52.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.52.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.52.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.52.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.52.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.53.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.53.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.53.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.53.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.53.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.53.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.54.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.54.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.54.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.54.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.54.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.54.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.55.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.55.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.55.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.55.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.55.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.55.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.56.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.56.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.56.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.56.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.56.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.56.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.57.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.57.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.57.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.57.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.57.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.57.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.58.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.58.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.58.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.58.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.58.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.58.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.59.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.59.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.59.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.59.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.59.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.59.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.6.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.6.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.6.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.60.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.60.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.60.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.60.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.60.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.60.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.61.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.61.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.61.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.61.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.61.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.61.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.62.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.62.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.62.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.62.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.62.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.62.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.63.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.63.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.63.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.63.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.63.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.63.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.64.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.64.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.64.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.64.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.64.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.64.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.65.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.65.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.65.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.65.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.65.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.65.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.66.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.66.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.66.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.66.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.66.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.66.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.67.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.67.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.67.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.67.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.67.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.67.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.68.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.68.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.68.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.68.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.68.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.68.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.69.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.69.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.69.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.69.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.69.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.69.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.7.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.7.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.7.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.70.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.70.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.70.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.70.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.70.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.70.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.71.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.71.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.71.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.71.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.71.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.71.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.72.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.72.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.72.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.72.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.72.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.72.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.73.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.73.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.73.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.73.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.73.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.73.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.74.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.74.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.74.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.74.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.74.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.74.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.75.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.75.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.75.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.75.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.75.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.75.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.76.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.76.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.76.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.76.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.76.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.76.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.77.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.77.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.77.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.77.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.77.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.77.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.78.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.78.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.78.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.78.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.78.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.78.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.79.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.79.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.79.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.79.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.79.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.79.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.8.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.8.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.8.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.8.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.8.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.8.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.80.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.80.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.80.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.80.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.80.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.80.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.81.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.81.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.81.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.81.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.81.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.81.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.82.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.82.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.82.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.82.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.82.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.82.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.83.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.83.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.83.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.83.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.83.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.83.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.84.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.84.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.84.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.84.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.84.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.84.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.85.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.85.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.85.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.85.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.85.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.85.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.86.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.86.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.86.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.86.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.86.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.86.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.87.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.87.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.87.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.87.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.87.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.87.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.88.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.88.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.88.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.88.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.88.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.88.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.89.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.89.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.89.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.89.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.89.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.89.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.9.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.9.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.9.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.9.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.9.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.9.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.90.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.90.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.90.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.90.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.90.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.90.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.91.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.91.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.91.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.91.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.91.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.91.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.92.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.92.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.92.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.92.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.92.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.92.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.93.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.93.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.93.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.93.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.93.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.93.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.94.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.94.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.94.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.94.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.94.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.94.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.95.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.95.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.95.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.95.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.95.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.95.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.96.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.96.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.96.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.96.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.96.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.96.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.97.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.97.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.97.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.97.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.97.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.97.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.98.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.98.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.98.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.98.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.98.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.98.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.99.w1.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.99.w1.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.99.w2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.99.w2.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.99.w3.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.experts.99.w3.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.shared_experts.down_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.shared_experts.gate_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.shared_experts.up_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.input_layernorm.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.post_attention_layernorm.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.index_k_norm.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.index_k_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.index_q_norm.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.index_q_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.k_norm.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.k_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.k_proj.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.o_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.o_proj.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.q_norm.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.q_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.q_proj.weight_scale": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.v_proj.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.26.self_attn.v_proj.weight_scale": "model-00026-of-00059.safetensors", - "multi_modal_projector.linear_1.weight": "model-00026-of-00059.safetensors", - "multi_modal_projector.linear_2.bias": "model-00026-of-00059.safetensors", - "multi_modal_projector.linear_2.weight": "model-00026-of-00059.safetensors", - "patch_merge_mlp.linear_1.bias": "model-00026-of-00059.safetensors", - "patch_merge_mlp.linear_1.weight": "model-00026-of-00059.safetensors", - "patch_merge_mlp.linear_2.bias": "model-00026-of-00059.safetensors", - "patch_merge_mlp.linear_2.weight": "model-00026-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.e_score_correction_bias": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.gate.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.e_score_correction_bias": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.0.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.0.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.0.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.1.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.1.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.1.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.10.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.10.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.10.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.100.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.100.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.100.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.101.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.101.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.101.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.102.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.102.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.102.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.103.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.103.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.103.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.104.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.104.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.104.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.105.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.105.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.105.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.106.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.106.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.106.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.107.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.107.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.107.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.108.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.108.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.108.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.109.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.109.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.109.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.11.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.11.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.11.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.110.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.110.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.110.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.111.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.111.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.111.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.112.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.112.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.112.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.113.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.113.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.113.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.114.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.114.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.114.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.115.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.115.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.115.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.116.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.116.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.116.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.116.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.116.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.116.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.117.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.117.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.117.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.117.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.117.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.117.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.118.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.118.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.118.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.118.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.118.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.118.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.119.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.119.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.119.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.119.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.119.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.119.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.12.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.12.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.12.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.120.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.120.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.120.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.120.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.120.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.120.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.121.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.121.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.121.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.121.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.121.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.121.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.122.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.122.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.122.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.122.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.122.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.122.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.123.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.123.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.123.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.123.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.123.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.123.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.124.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.124.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.124.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.124.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.124.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.124.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.125.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.125.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.125.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.125.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.125.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.125.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.126.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.126.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.126.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.126.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.126.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.126.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.127.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.127.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.127.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.127.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.127.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.127.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.13.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.13.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.13.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.14.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.14.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.14.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.15.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.15.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.15.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.16.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.16.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.16.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.17.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.17.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.17.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.18.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.18.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.18.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.19.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.19.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.19.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.2.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.2.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.2.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.20.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.20.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.20.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.21.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.21.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.21.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.22.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.22.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.22.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.23.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.23.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.23.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.24.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.24.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.24.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.25.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.25.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.25.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.26.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.26.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.26.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.27.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.27.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.27.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.28.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.28.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.28.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.29.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.29.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.29.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.3.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.3.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.3.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.30.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.30.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.30.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.31.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.31.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.31.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.32.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.32.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.32.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.32.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.32.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.32.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.33.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.33.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.33.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.33.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.33.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.33.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.34.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.34.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.34.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.34.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.34.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.34.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.35.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.35.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.35.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.35.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.35.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.35.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.36.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.36.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.36.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.36.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.36.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.36.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.37.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.37.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.37.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.37.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.37.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.37.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.38.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.38.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.38.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.38.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.38.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.38.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.39.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.39.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.39.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.39.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.39.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.39.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.4.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.4.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.4.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.40.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.40.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.40.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.40.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.40.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.40.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.41.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.41.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.41.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.41.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.41.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.41.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.42.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.42.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.42.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.42.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.42.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.42.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.43.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.43.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.43.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.43.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.43.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.43.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.44.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.44.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.44.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.44.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.44.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.44.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.45.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.45.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.45.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.45.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.45.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.45.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.46.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.46.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.46.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.46.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.46.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.46.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.47.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.47.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.47.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.47.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.47.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.47.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.48.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.48.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.48.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.48.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.48.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.48.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.49.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.49.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.49.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.49.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.49.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.49.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.5.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.5.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.5.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.50.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.50.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.50.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.50.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.50.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.50.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.51.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.51.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.51.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.51.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.51.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.51.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.52.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.52.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.52.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.52.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.52.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.52.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.53.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.53.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.53.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.53.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.53.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.53.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.54.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.54.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.54.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.54.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.54.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.54.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.55.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.55.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.55.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.55.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.55.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.55.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.56.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.56.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.56.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.56.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.56.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.56.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.57.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.57.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.57.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.57.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.57.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.57.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.58.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.58.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.58.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.58.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.58.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.58.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.59.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.59.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.59.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.59.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.59.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.59.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.6.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.6.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.6.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.60.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.60.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.60.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.60.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.60.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.60.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.61.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.61.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.61.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.61.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.61.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.61.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.62.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.62.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.62.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.62.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.62.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.62.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.63.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.63.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.63.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.63.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.63.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.63.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.64.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.64.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.64.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.64.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.64.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.64.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.65.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.65.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.65.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.65.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.65.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.65.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.66.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.66.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.66.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.66.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.66.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.66.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.67.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.67.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.67.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.67.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.67.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.67.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.68.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.68.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.68.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.68.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.68.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.68.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.69.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.69.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.69.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.69.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.69.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.69.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.7.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.7.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.7.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.70.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.70.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.70.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.70.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.70.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.70.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.71.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.71.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.71.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.71.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.71.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.71.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.72.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.72.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.72.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.72.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.72.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.72.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.73.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.73.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.73.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.73.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.73.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.73.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.74.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.74.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.74.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.74.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.74.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.74.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.75.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.75.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.75.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.75.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.75.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.75.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.76.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.76.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.76.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.76.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.76.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.76.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.77.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.77.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.77.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.77.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.77.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.77.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.78.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.78.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.78.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.78.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.78.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.78.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.79.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.79.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.79.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.79.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.79.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.79.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.8.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.8.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.8.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.80.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.80.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.80.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.80.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.80.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.80.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.81.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.81.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.81.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.81.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.81.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.81.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.82.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.82.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.82.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.82.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.82.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.82.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.83.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.83.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.83.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.83.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.83.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.83.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.84.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.84.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.84.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.84.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.84.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.84.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.85.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.85.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.85.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.85.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.85.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.85.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.86.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.86.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.86.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.86.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.86.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.86.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.87.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.87.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.87.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.87.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.87.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.87.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.88.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.88.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.88.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.88.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.88.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.88.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.89.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.89.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.89.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.89.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.89.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.89.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.9.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.9.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.9.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.90.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.90.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.90.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.90.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.90.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.90.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.91.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.91.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.91.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.91.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.91.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.91.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.92.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.92.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.92.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.92.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.92.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.92.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.93.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.93.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.93.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.93.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.93.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.93.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.94.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.94.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.94.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.94.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.94.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.94.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.95.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.95.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.95.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.95.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.95.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.95.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.96.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.96.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.96.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.96.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.96.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.96.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.97.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.97.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.97.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.97.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.97.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.97.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.98.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.98.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.98.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.98.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.98.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.98.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.99.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.99.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.99.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.99.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.99.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.experts.99.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.shared_experts.down_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.shared_experts.gate_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.shared_experts.up_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.input_layernorm.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.post_attention_layernorm.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.index_k_norm.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.index_k_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.index_q_norm.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.index_q_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.k_norm.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.k_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.k_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.o_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.o_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.q_norm.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.q_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.q_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.v_proj.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.11.self_attn.v_proj.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.0.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.0.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.0.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.1.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.1.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.1.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.10.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.10.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.10.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.100.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.100.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.100.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.101.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.101.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.101.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.102.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.102.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.102.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.103.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.103.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.103.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.104.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.104.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.104.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.105.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.105.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.105.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.106.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.106.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.106.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.107.w1.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.107.w2.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.107.w3.weight_scale": "model-00011-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.e_score_correction_bias": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.gate.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.0.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.0.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.0.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.1.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.1.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.1.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.10.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.10.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.10.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.10.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.10.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.10.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.100.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.100.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.100.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.100.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.100.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.100.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.101.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.101.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.101.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.101.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.101.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.101.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.102.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.102.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.102.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.102.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.102.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.102.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.103.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.103.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.103.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.103.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.103.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.103.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.104.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.104.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.104.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.104.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.104.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.104.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.105.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.105.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.105.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.105.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.105.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.105.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.106.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.106.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.106.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.106.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.106.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.106.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.107.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.107.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.107.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.107.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.107.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.107.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.108.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.108.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.108.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.108.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.108.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.108.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.109.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.109.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.109.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.109.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.109.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.109.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.11.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.11.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.11.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.11.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.11.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.11.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.110.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.110.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.110.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.110.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.110.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.110.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.111.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.111.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.111.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.111.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.111.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.111.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.112.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.112.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.112.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.112.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.112.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.112.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.113.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.113.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.113.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.113.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.113.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.113.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.114.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.114.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.114.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.114.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.114.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.114.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.115.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.115.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.115.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.115.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.115.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.115.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.116.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.116.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.116.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.116.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.116.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.116.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.117.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.117.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.117.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.117.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.117.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.117.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.118.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.118.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.118.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.118.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.118.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.118.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.119.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.119.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.119.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.119.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.119.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.119.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.12.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.12.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.12.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.12.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.12.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.12.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.120.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.120.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.120.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.120.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.120.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.120.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.121.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.121.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.121.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.121.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.121.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.121.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.122.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.122.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.122.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.122.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.122.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.122.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.123.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.123.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.123.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.123.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.123.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.123.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.124.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.124.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.124.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.124.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.124.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.124.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.125.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.125.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.125.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.125.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.125.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.125.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.126.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.126.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.126.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.126.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.126.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.126.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.127.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.127.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.127.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.127.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.127.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.127.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.13.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.13.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.13.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.13.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.13.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.13.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.14.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.14.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.14.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.14.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.14.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.14.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.15.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.15.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.15.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.15.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.15.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.15.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.16.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.16.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.16.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.16.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.16.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.16.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.17.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.17.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.17.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.17.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.17.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.17.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.18.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.18.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.18.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.18.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.18.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.18.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.19.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.19.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.19.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.19.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.19.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.19.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.2.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.2.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.2.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.20.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.20.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.20.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.20.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.20.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.20.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.21.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.21.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.21.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.21.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.21.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.21.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.22.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.22.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.22.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.22.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.22.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.22.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.23.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.23.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.23.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.23.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.23.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.23.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.24.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.24.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.24.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.24.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.24.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.24.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.25.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.25.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.25.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.25.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.25.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.25.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.26.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.26.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.26.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.26.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.26.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.26.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.27.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.27.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.27.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.27.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.27.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.27.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.28.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.28.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.28.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.28.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.28.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.28.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.29.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.29.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.29.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.29.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.29.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.29.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.3.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.3.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.3.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.30.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.30.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.30.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.30.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.30.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.30.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.31.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.31.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.31.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.31.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.31.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.31.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.32.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.32.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.32.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.32.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.32.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.32.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.33.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.33.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.33.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.33.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.33.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.33.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.34.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.34.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.34.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.34.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.34.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.34.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.35.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.35.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.35.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.35.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.35.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.35.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.36.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.36.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.36.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.36.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.36.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.36.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.37.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.37.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.37.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.37.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.37.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.37.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.38.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.38.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.38.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.38.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.38.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.38.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.39.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.39.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.39.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.39.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.39.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.39.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.4.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.4.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.4.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.40.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.40.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.40.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.40.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.40.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.40.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.41.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.41.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.41.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.41.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.41.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.41.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.42.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.42.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.42.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.42.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.42.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.42.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.43.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.43.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.43.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.43.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.43.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.43.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.44.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.44.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.44.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.44.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.44.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.44.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.45.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.45.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.45.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.45.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.45.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.45.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.46.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.46.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.46.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.46.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.46.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.46.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.47.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.47.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.47.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.47.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.47.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.47.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.48.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.48.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.48.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.48.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.48.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.48.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.49.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.49.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.49.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.49.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.49.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.49.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.5.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.5.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.5.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.50.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.50.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.50.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.50.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.50.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.50.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.51.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.51.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.51.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.51.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.51.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.51.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.52.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.52.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.52.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.52.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.52.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.52.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.53.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.53.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.53.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.53.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.53.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.53.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.54.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.54.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.54.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.54.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.54.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.54.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.55.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.55.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.55.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.55.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.55.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.55.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.56.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.56.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.56.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.56.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.56.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.56.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.57.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.57.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.57.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.57.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.57.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.57.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.58.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.58.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.58.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.58.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.58.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.58.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.59.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.59.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.59.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.59.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.59.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.59.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.6.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.6.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.6.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.60.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.60.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.60.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.60.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.60.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.60.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.61.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.61.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.61.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.61.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.61.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.61.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.62.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.62.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.62.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.62.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.62.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.62.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.63.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.63.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.63.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.63.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.63.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.63.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.64.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.64.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.64.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.64.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.64.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.64.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.65.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.65.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.65.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.65.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.65.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.65.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.66.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.66.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.66.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.66.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.66.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.66.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.67.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.67.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.67.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.67.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.67.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.67.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.68.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.68.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.68.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.68.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.68.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.68.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.69.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.69.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.69.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.69.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.69.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.69.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.7.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.7.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.7.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.70.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.70.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.70.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.70.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.70.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.70.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.71.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.71.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.71.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.71.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.71.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.71.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.72.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.72.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.72.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.72.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.72.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.72.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.73.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.73.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.73.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.73.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.73.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.73.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.74.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.74.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.74.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.74.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.74.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.74.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.75.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.75.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.75.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.75.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.75.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.75.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.76.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.76.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.76.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.76.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.76.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.76.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.77.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.77.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.77.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.77.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.77.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.77.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.78.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.78.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.78.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.78.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.78.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.78.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.79.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.79.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.79.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.79.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.79.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.79.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.8.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.8.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.8.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.8.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.8.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.8.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.80.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.80.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.80.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.80.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.80.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.80.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.81.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.81.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.81.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.81.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.81.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.81.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.82.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.82.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.82.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.82.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.82.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.82.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.83.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.83.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.83.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.83.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.83.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.83.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.84.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.84.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.84.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.84.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.84.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.84.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.85.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.85.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.85.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.85.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.85.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.85.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.86.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.86.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.86.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.86.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.86.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.86.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.87.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.87.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.87.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.87.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.87.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.87.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.88.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.88.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.88.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.88.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.88.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.88.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.89.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.89.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.89.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.89.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.89.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.89.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.9.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.9.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.9.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.9.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.9.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.9.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.90.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.90.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.90.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.90.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.90.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.90.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.91.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.91.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.91.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.91.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.91.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.91.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.92.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.92.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.92.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.92.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.92.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.92.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.93.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.93.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.93.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.93.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.93.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.93.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.94.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.94.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.94.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.94.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.94.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.94.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.95.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.95.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.95.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.95.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.95.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.95.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.96.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.96.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.96.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.96.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.96.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.96.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.97.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.97.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.97.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.97.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.97.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.97.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.98.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.98.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.98.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.98.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.98.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.98.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.99.w1.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.99.w1.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.99.w2.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.99.w2.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.99.w3.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.experts.99.w3.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.shared_experts.down_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.shared_experts.gate_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.shared_experts.up_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.input_layernorm.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.post_attention_layernorm.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.index_k_norm.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.index_k_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.index_q_norm.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.index_q_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.k_norm.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.k_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.k_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.o_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.o_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.q_norm.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.q_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.q_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.v_proj.weight": "model-00029-of-00059.safetensors", - "language_model.model.layers.29.self_attn.v_proj.weight_scale": "model-00029-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.e_score_correction_bias": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.gate.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.e_score_correction_bias": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.0.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.0.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.0.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.1.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.1.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.1.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.10.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.10.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.10.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.10.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.10.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.10.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.100.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.100.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.100.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.100.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.100.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.100.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.101.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.101.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.101.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.101.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.101.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.101.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.102.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.102.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.102.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.102.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.102.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.102.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.103.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.103.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.103.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.103.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.103.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.103.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.104.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.104.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.104.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.104.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.104.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.104.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.105.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.105.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.105.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.105.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.105.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.105.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.106.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.106.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.106.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.106.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.106.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.106.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.107.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.107.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.107.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.107.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.107.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.107.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.108.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.108.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.108.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.108.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.108.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.108.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.109.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.109.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.109.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.109.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.109.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.109.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.11.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.11.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.11.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.11.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.11.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.11.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.110.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.110.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.110.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.110.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.110.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.110.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.111.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.111.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.111.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.111.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.111.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.111.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.112.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.112.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.112.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.112.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.112.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.112.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.113.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.113.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.113.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.113.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.113.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.113.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.114.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.114.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.114.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.114.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.114.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.114.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.115.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.115.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.115.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.115.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.115.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.115.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.116.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.116.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.116.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.116.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.116.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.116.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.117.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.117.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.117.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.117.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.117.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.117.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.118.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.118.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.118.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.118.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.118.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.118.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.119.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.119.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.119.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.119.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.119.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.119.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.12.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.12.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.12.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.12.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.12.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.12.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.120.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.120.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.120.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.120.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.120.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.120.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.121.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.121.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.121.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.121.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.121.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.121.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.122.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.122.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.122.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.122.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.122.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.122.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.123.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.123.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.123.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.123.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.123.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.123.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.124.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.124.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.124.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.124.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.124.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.124.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.125.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.125.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.125.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.125.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.125.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.125.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.126.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.126.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.126.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.126.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.126.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.126.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.127.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.127.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.127.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.127.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.127.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.127.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.13.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.13.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.13.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.13.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.13.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.13.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.14.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.14.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.14.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.14.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.14.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.14.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.15.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.15.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.15.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.15.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.15.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.15.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.16.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.16.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.16.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.16.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.16.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.16.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.17.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.17.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.17.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.17.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.17.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.17.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.18.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.18.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.18.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.18.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.18.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.18.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.19.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.19.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.19.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.19.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.19.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.19.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.2.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.2.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.2.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.20.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.20.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.20.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.20.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.20.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.20.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.21.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.21.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.21.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.21.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.21.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.21.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.22.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.22.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.22.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.22.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.22.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.22.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.23.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.23.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.23.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.23.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.23.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.23.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.24.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.24.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.24.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.24.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.24.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.24.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.25.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.25.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.25.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.25.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.25.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.25.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.26.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.26.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.26.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.26.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.26.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.26.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.27.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.27.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.27.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.27.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.27.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.27.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.28.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.28.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.28.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.28.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.28.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.28.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.29.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.29.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.29.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.29.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.29.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.29.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.3.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.3.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.3.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.30.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.30.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.30.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.30.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.30.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.30.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.31.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.31.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.31.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.31.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.31.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.31.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.32.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.32.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.32.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.32.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.32.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.32.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.33.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.33.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.33.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.33.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.33.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.33.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.34.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.34.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.34.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.34.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.34.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.34.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.35.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.35.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.35.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.35.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.35.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.35.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.36.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.36.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.36.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.36.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.36.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.36.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.37.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.37.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.37.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.37.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.37.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.37.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.38.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.38.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.38.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.38.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.38.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.38.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.39.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.39.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.39.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.39.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.39.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.39.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.4.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.4.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.4.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.40.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.40.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.40.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.40.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.40.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.40.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.41.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.41.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.41.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.41.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.41.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.41.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.42.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.42.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.42.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.42.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.42.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.42.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.43.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.43.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.43.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.43.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.43.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.43.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.44.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.44.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.44.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.44.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.44.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.44.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.45.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.45.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.45.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.45.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.45.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.45.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.46.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.46.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.46.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.46.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.46.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.46.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.47.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.47.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.47.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.47.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.47.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.47.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.48.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.48.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.48.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.48.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.48.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.48.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.49.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.49.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.49.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.49.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.49.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.49.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.5.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.5.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.5.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.50.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.50.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.50.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.50.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.50.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.50.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.51.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.51.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.51.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.51.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.51.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.51.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.52.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.52.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.52.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.52.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.52.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.52.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.53.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.53.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.53.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.53.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.53.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.53.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.54.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.54.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.54.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.54.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.54.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.54.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.55.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.55.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.55.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.55.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.55.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.55.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.56.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.56.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.56.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.56.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.56.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.56.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.57.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.57.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.57.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.57.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.57.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.57.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.58.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.58.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.58.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.58.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.58.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.58.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.59.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.59.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.59.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.59.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.59.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.59.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.6.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.6.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.6.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.60.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.60.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.60.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.60.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.60.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.60.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.61.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.61.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.61.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.61.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.61.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.61.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.62.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.62.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.62.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.62.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.62.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.62.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.63.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.63.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.63.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.63.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.63.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.63.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.64.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.64.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.64.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.64.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.64.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.64.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.65.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.65.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.65.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.65.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.65.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.65.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.66.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.66.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.66.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.66.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.66.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.66.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.67.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.67.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.67.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.67.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.67.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.67.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.68.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.68.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.68.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.68.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.68.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.68.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.69.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.69.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.69.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.69.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.69.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.69.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.7.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.7.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.7.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.70.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.70.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.70.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.70.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.70.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.70.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.71.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.71.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.71.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.71.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.71.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.71.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.72.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.72.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.72.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.72.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.72.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.72.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.73.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.73.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.73.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.73.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.73.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.73.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.74.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.74.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.74.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.74.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.74.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.74.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.75.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.75.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.75.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.75.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.75.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.75.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.76.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.76.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.76.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.76.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.76.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.76.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.77.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.77.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.77.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.77.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.77.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.77.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.78.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.78.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.78.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.78.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.78.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.78.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.79.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.79.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.79.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.79.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.79.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.79.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.8.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.8.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.8.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.8.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.8.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.8.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.80.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.80.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.80.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.80.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.80.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.80.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.81.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.81.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.81.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.81.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.81.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.81.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.82.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.82.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.82.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.82.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.82.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.82.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.83.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.83.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.83.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.83.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.83.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.83.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.84.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.84.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.84.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.84.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.84.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.84.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.85.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.85.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.85.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.85.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.85.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.85.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.86.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.86.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.86.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.86.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.86.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.86.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.87.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.87.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.87.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.87.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.87.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.87.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.88.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.88.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.88.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.88.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.88.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.88.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.89.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.89.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.89.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.89.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.89.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.89.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.9.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.9.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.9.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.9.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.9.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.9.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.90.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.90.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.90.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.90.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.90.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.90.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.91.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.91.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.91.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.91.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.91.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.91.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.92.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.92.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.92.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.92.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.92.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.92.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.93.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.93.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.93.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.93.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.93.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.93.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.94.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.94.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.94.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.94.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.94.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.94.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.95.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.95.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.95.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.95.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.95.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.95.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.96.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.96.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.96.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.96.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.96.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.96.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.97.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.97.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.97.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.97.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.97.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.97.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.98.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.98.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.98.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.98.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.98.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.98.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.99.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.99.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.99.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.99.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.99.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.experts.99.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.shared_experts.down_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.shared_experts.gate_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.shared_experts.up_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.input_layernorm.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.post_attention_layernorm.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.index_k_norm.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.index_k_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.index_q_norm.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.index_q_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.k_norm.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.k_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.k_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.o_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.o_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.q_norm.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.q_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.q_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.v_proj.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.20.self_attn.v_proj.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.0.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.0.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.0.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.1.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.1.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.1.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.10.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.10.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.10.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.10.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.10.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.10.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.100.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.100.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.100.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.100.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.100.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.100.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.101.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.101.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.101.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.101.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.101.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.101.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.102.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.102.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.102.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.102.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.102.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.102.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.103.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.103.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.103.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.103.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.103.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.103.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.104.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.104.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.104.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.104.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.104.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.104.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.105.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.105.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.105.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.105.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.105.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.105.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.106.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.106.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.106.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.106.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.106.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.106.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.107.w1.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.107.w1.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.107.w2.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.107.w2.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.107.w3.weight": "model-00020-of-00059.safetensors", - "language_model.model.layers.54.block_sparse_moe.experts.107.w3.weight_scale": "model-00020-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.e_score_correction_bias": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.e_score_correction_bias": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.0.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.0.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.0.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.1.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.1.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.1.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.10.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.10.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.10.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.100.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.100.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.100.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.101.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.101.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.101.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.102.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.102.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.102.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.103.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.103.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.103.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.104.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.104.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.104.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.105.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.105.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.105.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.106.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.106.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.106.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.107.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.107.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.38.block_sparse_moe.experts.107.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.0.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.0.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.0.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.1.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.1.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.1.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.10.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.10.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.10.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.100.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.100.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.100.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.101.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.101.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.101.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.102.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.102.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.102.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.103.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.103.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.103.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.104.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.104.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.104.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.105.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.105.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.105.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.106.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.106.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.106.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.107.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.107.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.107.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.108.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.108.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.108.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.108.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.108.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.108.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.109.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.109.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.109.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.109.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.109.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.109.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.11.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.11.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.11.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.110.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.110.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.110.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.110.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.110.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.110.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.111.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.111.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.111.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.111.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.111.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.111.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.112.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.112.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.112.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.112.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.112.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.112.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.113.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.113.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.113.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.113.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.113.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.113.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.114.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.114.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.114.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.114.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.114.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.114.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.115.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.115.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.115.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.115.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.115.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.115.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.116.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.116.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.116.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.116.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.116.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.116.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.117.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.117.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.117.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.117.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.117.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.117.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.118.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.118.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.118.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.118.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.118.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.118.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.119.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.119.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.119.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.119.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.119.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.119.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.12.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.12.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.12.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.120.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.120.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.120.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.120.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.120.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.120.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.121.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.121.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.121.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.121.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.121.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.121.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.122.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.122.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.122.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.122.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.122.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.122.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.123.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.123.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.123.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.123.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.123.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.123.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.124.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.124.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.124.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.124.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.124.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.124.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.125.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.125.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.125.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.125.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.125.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.125.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.126.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.126.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.126.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.126.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.126.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.126.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.127.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.127.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.127.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.127.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.127.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.127.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.13.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.13.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.13.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.14.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.14.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.14.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.15.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.15.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.15.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.16.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.16.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.16.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.17.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.17.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.17.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.18.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.18.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.18.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.19.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.19.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.19.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.2.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.2.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.2.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.20.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.20.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.20.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.21.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.21.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.21.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.22.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.22.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.22.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.23.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.23.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.23.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.24.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.24.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.24.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.25.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.25.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.25.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.26.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.26.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.26.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.27.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.27.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.27.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.28.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.28.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.28.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.29.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.29.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.29.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.3.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.3.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.3.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.30.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.30.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.30.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.31.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.31.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.31.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.32.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.32.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.32.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.33.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.33.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.33.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.34.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.34.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.34.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.35.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.35.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.35.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.36.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.36.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.36.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.37.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.37.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.37.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.38.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.38.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.38.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.39.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.39.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.39.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.4.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.4.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.4.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.40.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.40.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.40.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.41.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.41.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.41.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.42.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.42.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.42.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.43.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.43.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.43.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.44.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.44.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.44.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.45.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.45.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.45.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.46.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.46.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.46.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.47.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.47.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.47.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.48.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.48.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.48.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.49.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.49.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.49.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.5.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.5.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.5.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.50.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.50.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.50.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.51.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.51.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.51.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.52.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.52.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.52.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.53.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.53.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.53.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.54.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.54.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.54.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.55.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.55.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.55.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.56.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.56.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.56.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.57.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.57.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.57.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.58.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.58.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.58.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.59.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.59.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.59.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.6.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.6.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.6.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.60.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.60.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.60.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.61.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.61.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.61.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.62.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.62.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.62.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.63.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.63.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.63.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.64.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.64.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.64.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.64.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.64.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.64.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.65.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.65.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.65.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.65.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.65.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.65.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.66.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.66.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.66.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.66.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.66.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.66.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.67.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.67.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.67.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.67.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.67.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.67.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.68.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.68.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.68.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.68.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.68.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.68.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.69.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.69.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.69.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.69.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.69.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.69.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.7.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.7.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.7.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.70.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.70.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.70.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.70.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.70.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.70.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.71.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.71.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.71.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.71.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.71.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.71.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.72.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.72.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.72.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.72.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.72.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.72.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.73.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.73.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.73.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.73.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.73.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.73.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.74.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.74.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.74.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.74.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.74.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.74.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.75.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.75.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.75.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.75.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.75.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.75.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.76.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.76.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.76.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.76.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.76.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.76.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.77.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.77.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.77.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.77.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.77.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.77.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.78.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.78.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.78.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.78.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.78.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.78.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.79.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.79.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.79.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.79.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.79.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.79.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.8.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.8.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.8.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.80.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.80.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.80.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.80.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.80.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.80.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.81.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.81.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.81.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.81.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.81.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.81.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.82.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.82.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.82.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.82.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.83.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.83.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.83.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.84.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.84.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.84.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.85.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.85.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.85.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.86.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.86.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.86.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.87.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.87.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.87.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.88.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.88.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.88.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.89.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.89.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.89.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.9.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.9.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.9.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.90.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.90.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.90.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.90.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.91.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.91.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.91.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.91.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.91.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.91.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.92.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.92.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.92.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.92.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.92.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.92.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.93.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.93.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.93.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.93.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.93.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.93.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.94.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.94.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.94.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.94.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.94.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.94.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.95.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.95.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.95.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.95.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.95.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.95.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.96.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.96.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.96.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.96.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.96.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.96.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.97.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.97.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.97.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.97.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.97.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.97.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.98.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.98.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.98.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.98.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.98.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.98.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.99.w1.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.99.w1.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.99.w2.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.99.w2.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.99.w3.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.experts.99.w3.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.shared_experts.down_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.shared_experts.gate_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.shared_experts.up_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.input_layernorm.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.post_attention_layernorm.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.index_k_norm.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.index_k_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.index_q_norm.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.index_q_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.k_norm.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.k_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.o_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.q_norm.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.q_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00059.safetensors", - "language_model.model.layers.4.self_attn.v_proj.weight_scale": "model-00004-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.e_score_correction_bias": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.mlp.down_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.mlp.gate_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.mlp.up_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.k_norm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.k_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.o_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.q_norm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.q_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.1.self_attn.v_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.mlp.down_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.mlp.gate_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.mlp.up_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.k_norm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.k_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.o_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.q_norm.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.q_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.2.self_attn.v_proj.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.0.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.0.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.0.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.1.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.1.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.1.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.10.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.10.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.10.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.100.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.100.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.100.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.100.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.100.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.100.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.101.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.101.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.101.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.101.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.101.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.101.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.102.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.102.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.102.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.102.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.102.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.102.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.103.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.103.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.103.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.103.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.103.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.103.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.104.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.104.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.104.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.104.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.104.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.104.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.105.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.105.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.105.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.105.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.105.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.105.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.106.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.106.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.106.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.106.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.106.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.106.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.107.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.107.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.107.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.107.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.107.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.107.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.108.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.108.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.108.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.108.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.108.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.108.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.109.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.109.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.109.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.109.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.109.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.109.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.11.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.11.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.11.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.110.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.110.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.110.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.110.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.110.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.110.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.111.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.111.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.111.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.111.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.111.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.111.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.112.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.112.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.112.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.112.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.112.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.112.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.113.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.113.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.113.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.113.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.113.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.113.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.114.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.114.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.114.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.114.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.114.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.114.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.115.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.115.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.115.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.115.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.115.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.115.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.116.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.116.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.116.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.116.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.116.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.116.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.117.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.117.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.117.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.117.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.117.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.117.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.118.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.118.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.118.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.118.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.118.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.118.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.119.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.119.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.119.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.119.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.119.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.119.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.12.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.12.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.12.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.120.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.120.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.120.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.120.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.120.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.120.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.121.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.121.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.121.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.121.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.121.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.121.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.122.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.122.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.122.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.122.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.122.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.122.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.123.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.123.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.123.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.123.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.123.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.123.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.124.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.124.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.124.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.124.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.124.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.124.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.125.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.125.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.125.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.125.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.125.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.125.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.126.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.126.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.126.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.126.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.126.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.126.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.127.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.127.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.127.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.127.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.127.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.127.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.13.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.13.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.13.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.14.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.14.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.14.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.15.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.15.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.15.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.16.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.16.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.16.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.17.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.17.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.17.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.18.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.18.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.18.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.19.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.19.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.19.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.2.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.2.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.2.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.20.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.20.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.20.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.21.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.21.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.21.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.22.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.22.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.22.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.23.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.23.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.23.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.24.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.24.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.24.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.25.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.25.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.25.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.26.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.26.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.26.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.27.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.27.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.27.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.28.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.28.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.28.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.29.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.29.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.29.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.3.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.3.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.3.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.30.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.30.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.30.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.31.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.31.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.31.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.32.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.32.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.32.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.33.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.33.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.33.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.34.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.34.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.34.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.35.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.35.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.35.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.36.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.36.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.36.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.37.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.37.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.37.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.38.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.38.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.38.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.39.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.39.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.39.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.4.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.4.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.4.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.40.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.40.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.40.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.41.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.41.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.41.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.42.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.42.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.42.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.43.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.43.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.43.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.44.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.44.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.44.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.45.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.45.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.45.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.46.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.46.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.46.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.47.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.47.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.47.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.48.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.48.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.48.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.49.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.49.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.49.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.5.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.5.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.5.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.50.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.50.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.50.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.51.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.51.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.51.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.52.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.52.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.52.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.53.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.53.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.53.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.54.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.54.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.54.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.55.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.55.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.55.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.56.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.56.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.56.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.57.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.57.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.57.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.58.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.58.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.58.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.59.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.59.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.59.w3.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.6.w1.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00059.safetensors", - "language_model.model.layers.25.block_sparse_moe.experts.6.w2.weight_scale": "model-00002-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.e_score_correction_bias": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.gate.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.e_score_correction_bias": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.0.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.0.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.0.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.1.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.1.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.1.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.10.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.10.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.10.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.100.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.100.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.100.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.101.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.101.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.101.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.102.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.102.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.102.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.103.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.103.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.103.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.104.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.104.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.104.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.105.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.105.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.105.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.106.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.106.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.106.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.107.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.107.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.107.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.108.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.108.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.108.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.108.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.108.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.108.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.109.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.109.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.109.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.109.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.109.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.109.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.11.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.11.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.11.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.11.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.11.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.11.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.110.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.110.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.110.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.110.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.110.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.110.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.111.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.111.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.111.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.111.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.111.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.111.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.112.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.112.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.112.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.112.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.112.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.112.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.113.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.113.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.113.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.113.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.113.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.113.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.114.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.114.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.114.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.114.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.114.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.114.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.115.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.115.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.115.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.115.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.115.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.115.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.116.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.116.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.116.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.116.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.116.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.116.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.117.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.117.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.117.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.117.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.117.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.117.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.118.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.118.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.118.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.118.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.118.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.118.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.119.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.119.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.119.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.119.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.119.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.119.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.12.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.12.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.12.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.12.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.12.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.12.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.120.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.120.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.120.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.120.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.120.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.120.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.121.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.121.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.121.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.121.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.121.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.121.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.122.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.122.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.122.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.122.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.122.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.122.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.123.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.123.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.123.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.123.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.123.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.123.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.124.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.124.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.124.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.124.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.124.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.124.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.125.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.125.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.125.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.125.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.125.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.125.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.126.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.126.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.126.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.126.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.126.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.126.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.127.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.127.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.127.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.127.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.127.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.127.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.13.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.13.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.13.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.13.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.13.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.13.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.14.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.14.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.14.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.14.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.14.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.14.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.15.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.15.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.15.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.15.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.15.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.15.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.16.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.16.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.16.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.16.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.16.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.16.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.17.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.17.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.17.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.17.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.17.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.17.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.18.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.18.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.18.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.18.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.18.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.18.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.19.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.19.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.19.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.19.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.19.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.19.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.2.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.2.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.2.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.20.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.20.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.20.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.20.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.20.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.20.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.21.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.21.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.21.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.21.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.21.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.21.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.22.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.22.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.22.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.22.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.22.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.22.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.23.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.23.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.23.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.23.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.23.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.23.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.24.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.24.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.24.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.24.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.24.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.24.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.25.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.25.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.25.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.25.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.25.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.25.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.26.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.26.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.26.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.26.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.26.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.26.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.27.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.27.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.27.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.27.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.27.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.27.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.28.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.28.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.28.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.28.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.28.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.28.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.29.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.29.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.29.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.29.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.29.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.29.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.3.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.3.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.3.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.30.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.30.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.30.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.30.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.30.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.30.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.31.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.31.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.31.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.31.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.31.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.31.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.32.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.32.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.32.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.32.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.32.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.32.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.33.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.33.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.33.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.33.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.33.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.33.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.34.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.34.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.34.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.34.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.34.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.34.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.35.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.35.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.35.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.35.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.35.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.35.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.36.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.36.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.36.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.36.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.36.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.36.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.37.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.37.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.37.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.37.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.37.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.37.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.38.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.38.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.38.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.38.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.38.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.38.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.39.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.39.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.39.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.39.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.39.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.39.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.4.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.4.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.4.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.40.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.40.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.40.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.40.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.40.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.40.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.41.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.41.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.41.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.41.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.41.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.41.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.42.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.42.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.42.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.42.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.42.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.42.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.43.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.43.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.43.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.43.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.43.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.43.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.44.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.44.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.44.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.44.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.44.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.44.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.45.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.45.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.45.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.45.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.45.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.45.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.46.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.46.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.46.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.46.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.46.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.46.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.47.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.47.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.47.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.47.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.47.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.47.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.48.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.48.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.48.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.48.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.48.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.48.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.49.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.49.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.49.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.49.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.49.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.49.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.5.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.5.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.5.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.50.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.50.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.50.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.50.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.50.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.50.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.51.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.51.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.51.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.51.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.51.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.51.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.52.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.52.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.52.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.52.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.52.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.52.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.53.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.53.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.53.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.53.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.53.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.53.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.54.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.54.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.54.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.54.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.54.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.54.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.55.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.55.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.55.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.55.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.55.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.55.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.56.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.56.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.56.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.56.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.56.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.56.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.57.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.57.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.57.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.57.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.57.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.57.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.58.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.58.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.58.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.58.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.58.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.58.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.59.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.59.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.59.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.59.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.59.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.59.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.6.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.6.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.6.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.60.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.60.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.60.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.60.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.60.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.60.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.61.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.61.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.61.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.61.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.61.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.61.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.62.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.62.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.62.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.62.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.62.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.62.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.63.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.63.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.63.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.63.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.63.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.63.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.64.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.64.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.64.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.64.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.64.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.64.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.65.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.65.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.65.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.65.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.65.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.65.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.66.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.66.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.66.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.66.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.66.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.66.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.67.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.67.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.67.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.67.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.67.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.67.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.68.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.68.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.68.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.68.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.68.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.68.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.69.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.69.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.69.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.69.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.69.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.69.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.7.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.7.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.7.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.70.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.70.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.70.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.70.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.70.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.70.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.71.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.71.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.71.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.71.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.71.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.71.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.72.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.72.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.72.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.72.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.72.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.72.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.73.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.73.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.73.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.73.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.73.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.73.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.74.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.74.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.74.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.74.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.74.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.74.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.75.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.75.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.75.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.75.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.75.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.75.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.76.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.76.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.76.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.76.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.76.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.76.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.77.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.77.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.77.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.77.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.77.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.77.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.78.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.78.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.78.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.78.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.78.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.78.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.79.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.79.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.79.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.79.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.79.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.79.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.8.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.8.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.8.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.8.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.8.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.8.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.80.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.80.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.80.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.80.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.80.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.80.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.81.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.81.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.81.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.81.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.81.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.81.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.82.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.82.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.82.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.82.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.82.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.82.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.83.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.83.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.83.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.83.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.83.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.83.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.84.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.84.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.84.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.84.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.84.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.84.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.85.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.85.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.85.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.85.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.85.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.85.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.86.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.86.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.86.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.86.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.86.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.86.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.87.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.87.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.87.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.87.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.87.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.87.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.88.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.88.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.88.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.88.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.88.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.88.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.89.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.89.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.89.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.89.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.89.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.89.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.9.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.9.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.9.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.9.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.9.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.9.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.90.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.90.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.90.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.90.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.90.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.90.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.91.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.91.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.91.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.91.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.91.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.91.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.92.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.92.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.92.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.92.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.92.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.92.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.93.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.93.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.93.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.93.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.93.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.93.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.94.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.94.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.94.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.94.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.94.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.94.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.95.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.95.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.95.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.95.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.95.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.95.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.96.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.96.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.96.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.96.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.96.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.96.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.97.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.97.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.97.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.97.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.97.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.97.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.98.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.98.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.98.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.98.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.98.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.98.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.99.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.99.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.99.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.99.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.99.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.experts.99.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.shared_experts.down_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.shared_experts.gate_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.shared_experts.up_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.input_layernorm.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.post_attention_layernorm.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.index_k_norm.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.index_k_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.index_q_norm.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.index_q_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.k_norm.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.k_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.k_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.o_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.o_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.q_norm.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.q_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.q_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.v_proj.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.18.self_attn.v_proj.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.0.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.0.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.0.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.1.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.1.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.1.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.10.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.10.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.10.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.100.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.100.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.100.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.101.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.101.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.101.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.102.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.102.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.102.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.103.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.103.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.103.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.104.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.104.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.104.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.105.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.105.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.105.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.106.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.106.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.106.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.107.w1.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.107.w2.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00059.safetensors", - "language_model.model.layers.52.block_sparse_moe.experts.107.w3.weight_scale": "model-00018-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.gate.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.108.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.108.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.108.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.108.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.108.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.108.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.109.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.109.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.109.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.109.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.109.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.109.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.11.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.11.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.11.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.11.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.11.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.11.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.110.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.110.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.110.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.110.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.110.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.110.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.111.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.111.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.111.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.111.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.111.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.111.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.112.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.112.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.112.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.112.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.112.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.112.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.113.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.113.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.113.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.113.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.113.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.113.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.114.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.114.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.114.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.114.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.114.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.114.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.115.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.115.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.115.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.115.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.115.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.115.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.116.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.116.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.116.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.116.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.116.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.116.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.117.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.117.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.117.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.117.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.117.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.117.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.118.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.118.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.118.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.118.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.118.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.118.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.119.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.119.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.119.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.119.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.119.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.119.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.12.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.12.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.12.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.12.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.12.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.12.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.120.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.120.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.120.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.120.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.120.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.120.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.121.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.121.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.121.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.121.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.121.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.121.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.122.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.122.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.122.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.122.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.122.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.122.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.123.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.123.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.123.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.123.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.123.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.123.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.124.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.124.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.124.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.124.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.124.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.124.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.125.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.125.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.125.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.125.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.125.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.125.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.126.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.126.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.126.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.126.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.126.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.126.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.127.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.127.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.127.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.127.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.127.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.127.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.13.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.13.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.13.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.13.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.13.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.13.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.14.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.14.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.14.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.14.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.14.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.14.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.15.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.15.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.15.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.15.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.15.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.15.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.16.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.16.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.16.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.16.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.16.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.16.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.17.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.17.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.17.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.17.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.17.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.17.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.18.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.18.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.18.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.18.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.18.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.18.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.19.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.19.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.19.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.19.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.19.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.19.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.2.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.2.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.2.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.20.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.20.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.20.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.20.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.20.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.20.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.21.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.21.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.21.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.21.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.21.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.21.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.22.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.22.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.22.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.22.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.22.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.22.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.23.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.23.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.23.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.23.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.23.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.23.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.24.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.24.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.24.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.24.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.24.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.24.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.25.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.25.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.25.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.25.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.25.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.25.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.26.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.26.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.26.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.26.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.26.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.26.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.27.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.27.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.27.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.27.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.27.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.27.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.28.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.28.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.28.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.28.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.28.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.28.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.29.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.29.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.29.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.29.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.29.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.29.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.3.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.3.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.3.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.30.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.30.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.30.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.30.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.30.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.30.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.31.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.31.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.31.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.31.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.31.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.31.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.32.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.32.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.32.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.32.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.32.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.32.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.33.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.33.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.33.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.33.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.33.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.33.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.34.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.34.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.34.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.34.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.34.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.34.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.35.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.35.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.35.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.35.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.35.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.35.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.36.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.36.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.36.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.36.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.36.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.36.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.37.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.37.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.37.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.37.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.37.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.37.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.38.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.38.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.38.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.38.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.38.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.38.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.39.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.39.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.39.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.39.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.39.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.39.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.4.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.4.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.4.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.40.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.40.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.40.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.40.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.40.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.40.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.41.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.41.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.41.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.41.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.41.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.41.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.42.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.42.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.42.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.42.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.42.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.42.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.43.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.43.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.43.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.43.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.43.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.43.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.44.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.44.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.44.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.44.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.44.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.44.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.45.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.45.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.45.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.45.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.45.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.45.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.46.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.46.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.46.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.46.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.46.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.46.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.47.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.47.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.47.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.47.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.47.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.47.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.48.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.48.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.48.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.48.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.48.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.48.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.49.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.49.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.49.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.49.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.49.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.49.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.5.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.5.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.5.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.5.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.50.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.50.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.50.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.50.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.50.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.50.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.51.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.51.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.51.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.51.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.51.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.51.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.52.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.52.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.52.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.52.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.52.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.52.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.53.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.53.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.53.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.53.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.53.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.53.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.54.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.54.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.54.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.54.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.54.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.54.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.55.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.55.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.55.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.55.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.55.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.55.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.56.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.56.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.56.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.56.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.56.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.56.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.57.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.57.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.57.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.57.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.57.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.57.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.58.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.58.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.58.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.58.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.58.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.58.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.59.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.59.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.59.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.59.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.59.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.59.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.6.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.6.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.6.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.6.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.6.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.6.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.60.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.60.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.60.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.60.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.60.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.60.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.61.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.61.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.61.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.61.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.61.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.61.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.62.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.62.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.62.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.62.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.62.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.62.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.63.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.63.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.63.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.63.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.63.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.63.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.64.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.64.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.64.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.64.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.64.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.64.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.65.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.65.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.65.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.65.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.65.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.65.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.66.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.66.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.66.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.66.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.66.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.66.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.67.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.67.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.67.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.67.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.67.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.67.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.68.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.68.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.68.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.68.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.68.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.68.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.69.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.69.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.69.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.69.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.69.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.69.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.7.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.7.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.7.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.7.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.7.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.7.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.70.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.70.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.70.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.70.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.70.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.70.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.71.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.71.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.71.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.71.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.71.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.71.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.72.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.72.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.72.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.72.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.72.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.72.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.73.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.73.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.73.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.73.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.73.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.73.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.74.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.74.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.74.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.74.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.74.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.74.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.75.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.75.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.75.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.75.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.75.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.75.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.76.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.76.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.76.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.76.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.76.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.76.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.77.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.77.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.77.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.77.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.77.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.77.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.78.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.78.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.78.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.78.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.78.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.78.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.79.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.79.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.79.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.79.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.79.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.79.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.8.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.8.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.8.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.8.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.8.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.8.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.80.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.80.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.80.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.80.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.80.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.80.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.81.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.81.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.81.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.81.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.81.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.81.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.82.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.82.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.82.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.82.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.82.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.82.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.83.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.83.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.83.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.83.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.83.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.83.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.84.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.84.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.84.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.84.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.84.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.84.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.85.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.85.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.85.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.85.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.85.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.85.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.86.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.86.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.86.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.86.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.86.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.86.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.87.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.87.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.87.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.87.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.87.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.87.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.88.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.88.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.88.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.88.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.88.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.88.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.89.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.89.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.89.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.89.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.89.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.89.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.9.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.9.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.9.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.9.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.9.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.9.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.90.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.90.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.90.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.90.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.90.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.90.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.91.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.91.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.91.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.91.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.91.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.91.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.92.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.92.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.92.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.92.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.92.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.92.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.93.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.93.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.93.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.93.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.93.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.93.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.94.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.94.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.94.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.94.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.94.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.94.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.95.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.95.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.95.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.95.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.95.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.95.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.96.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.96.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.96.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.96.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.96.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.96.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.97.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.97.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.97.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.97.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.97.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.97.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.98.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.98.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.98.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.98.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.98.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.98.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.99.w1.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.99.w1.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.99.w2.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.99.w2.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.99.w3.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.experts.99.w3.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.shared_experts.down_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.shared_experts.gate_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.shared_experts.up_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.input_layernorm.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.post_attention_layernorm.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.index_k_norm.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.index_k_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.index_q_norm.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.index_q_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.k_norm.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.k_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.k_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.o_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.o_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.q_norm.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.q_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.q_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.v_proj.weight": "model-00045-of-00059.safetensors", - "language_model.model.layers.45.self_attn.v_proj.weight_scale": "model-00045-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.e_score_correction_bias": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.e_score_correction_bias": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.0.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.0.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.0.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.1.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.1.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.1.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.10.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.10.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.10.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.100.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.100.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.100.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.101.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.101.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.101.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.102.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.102.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.102.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.103.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.103.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.103.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.104.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.104.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.104.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.105.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.105.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.105.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.106.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.106.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.106.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.107.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.107.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.107.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.108.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.108.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.108.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.108.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.108.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.108.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.109.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.109.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.109.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.109.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.109.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.109.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.11.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.11.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.11.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.110.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.110.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.110.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.110.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.110.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.110.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.111.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.111.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.111.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.111.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.111.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.111.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.112.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.112.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.112.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.112.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.112.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.112.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.113.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.113.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.113.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.113.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.113.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.113.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.114.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.114.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.114.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.114.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.114.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.114.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.115.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.115.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.115.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.115.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.115.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.115.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.116.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.116.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.116.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.116.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.116.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.116.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.117.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.117.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.117.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.117.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.117.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.117.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.118.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.118.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.118.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.118.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.118.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.118.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.119.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.119.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.119.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.119.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.119.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.119.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.12.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.12.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.12.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.120.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.120.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.120.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.120.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.120.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.120.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.121.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.121.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.121.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.121.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.121.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.121.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.122.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.122.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.122.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.122.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.122.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.122.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.123.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.123.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.123.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.123.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.123.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.123.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.124.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.124.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.124.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.124.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.124.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.124.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.125.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.125.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.125.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.125.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.125.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.125.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.126.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.126.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.126.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.126.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.126.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.126.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.127.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.127.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.127.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.127.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.127.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.127.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.13.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.13.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.13.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.14.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.14.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.14.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.15.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.15.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.15.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.16.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.16.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.16.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.17.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.17.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.17.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.18.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.18.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.18.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.19.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.19.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.19.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.2.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.2.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.2.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.20.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.20.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.20.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.21.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.21.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.21.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.22.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.22.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.22.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.23.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.23.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.23.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.24.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.24.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.24.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.25.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.25.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.25.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.26.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.26.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.26.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.27.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.27.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.27.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.28.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.28.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.28.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.29.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.29.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.29.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.3.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.3.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.3.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.30.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.30.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.30.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.31.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.31.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.31.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.32.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.32.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.32.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.33.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.33.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.33.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.34.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.34.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.34.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.34.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.35.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.35.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.35.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.36.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.36.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.36.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.37.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.37.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.37.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.38.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.38.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.38.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.38.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.39.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.39.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.39.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.4.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.4.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.4.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.40.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.40.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.40.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.41.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.41.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.41.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.42.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.42.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.42.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.43.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.43.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.43.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.44.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.44.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.44.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.45.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.45.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.45.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.46.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.46.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.46.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.47.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.47.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.47.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.48.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.48.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.48.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.49.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.49.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.49.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.5.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.5.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.5.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.50.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.50.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.50.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.51.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.51.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.51.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.52.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.52.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.52.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.53.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.53.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.53.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.54.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.54.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.54.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.55.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.55.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.55.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.56.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.56.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.56.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.57.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.57.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.57.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.58.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.58.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.58.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.59.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.59.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.59.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.6.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.6.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.6.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.60.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.60.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.60.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.61.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.61.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.61.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.62.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.62.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.62.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.63.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.63.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.63.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.64.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.64.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.64.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.65.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.65.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.65.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.66.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.66.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.66.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.67.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.67.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.67.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.67.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.67.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.67.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.68.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.68.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.68.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.68.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.68.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.68.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.69.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.69.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.69.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.69.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.69.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.69.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.7.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.7.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.7.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.70.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.70.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.70.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.70.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.70.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.70.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.71.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.71.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.71.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.71.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.71.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.71.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.72.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.72.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.72.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.72.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.72.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.72.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.73.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.73.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.73.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.73.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.73.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.73.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.74.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.74.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.74.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.74.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.74.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.74.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.75.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.75.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.75.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.75.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.75.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.75.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.76.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.76.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.76.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.76.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.76.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.76.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.77.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.77.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.77.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.77.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.77.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.77.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.78.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.78.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.78.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.78.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.78.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.78.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.79.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.79.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.79.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.79.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.79.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.79.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.8.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.8.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.8.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.80.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.80.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.80.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.80.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.80.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.80.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.81.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.81.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.81.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.81.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.81.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.81.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.82.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.82.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.82.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.82.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.82.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.82.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.83.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.83.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.83.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.83.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.83.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.83.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.84.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.84.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.84.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.84.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.84.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.84.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.85.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.85.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.85.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.85.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.85.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.85.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.86.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.86.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.86.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.86.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.86.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.86.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.87.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.87.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.87.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.87.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.87.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.87.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.88.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.88.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.88.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.88.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.88.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.88.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.89.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.89.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.89.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.89.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.89.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.89.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.9.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.9.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.9.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.90.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.90.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.90.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.90.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.90.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.90.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.91.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.91.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.91.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.91.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.91.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.91.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.92.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.92.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.92.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.92.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.92.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.92.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.93.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.93.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.93.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.93.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.93.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.93.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.94.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.94.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.94.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.94.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.94.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.94.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.95.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.95.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.95.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.95.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.95.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.95.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.96.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.96.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.96.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.96.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.96.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.96.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.97.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.97.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.97.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.97.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.97.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.97.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.98.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.98.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.98.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.98.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.98.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.98.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.99.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.99.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.99.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.99.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.99.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.experts.99.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.shared_experts.down_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.shared_experts.gate_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.shared_experts.up_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.index_k_norm.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.index_k_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.index_q_norm.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.index_q_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.k_norm.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.k_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.o_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.q_norm.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.q_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.3.self_attn.v_proj.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.0.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.0.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.0.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.1.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.1.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.1.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.10.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.10.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.10.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.100.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.100.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.100.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.101.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.101.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.101.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.102.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.102.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.102.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.103.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.103.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.103.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.104.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.104.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.104.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.105.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.105.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.105.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.106.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.106.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.106.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.107.w1.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.107.w2.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.107.w3.weight_scale": "model-00003-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.gate.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.108.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.108.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.108.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.108.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.108.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.108.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.109.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.109.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.109.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.109.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.109.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.109.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.11.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.11.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.11.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.11.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.11.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.11.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.110.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.110.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.110.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.110.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.110.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.110.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.111.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.111.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.111.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.111.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.111.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.111.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.112.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.112.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.112.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.112.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.112.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.112.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.113.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.113.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.113.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.113.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.113.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.113.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.114.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.114.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.114.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.114.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.114.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.114.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.115.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.115.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.115.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.115.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.115.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.115.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.116.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.116.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.116.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.116.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.116.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.116.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.117.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.117.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.117.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.117.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.117.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.117.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.118.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.118.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.118.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.118.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.118.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.118.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.119.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.119.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.119.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.119.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.119.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.119.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.12.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.12.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.12.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.12.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.12.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.12.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.120.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.120.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.120.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.120.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.120.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.120.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.121.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.121.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.121.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.121.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.121.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.121.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.122.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.122.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.122.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.122.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.122.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.122.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.123.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.123.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.123.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.123.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.123.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.123.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.124.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.124.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.124.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.124.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.124.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.124.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.125.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.125.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.125.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.125.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.125.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.125.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.126.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.126.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.126.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.126.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.126.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.126.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.127.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.127.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.127.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.127.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.127.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.127.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.13.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.13.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.13.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.13.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.13.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.13.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.14.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.14.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.14.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.14.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.14.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.14.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.15.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.15.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.15.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.15.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.15.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.15.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.16.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.16.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.16.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.16.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.16.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.16.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.17.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.17.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.17.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.17.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.17.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.17.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.18.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.18.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.18.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.18.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.18.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.18.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.19.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.19.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.19.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.19.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.19.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.19.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.2.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.2.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.2.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.20.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.20.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.20.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.20.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.20.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.20.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.21.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.21.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.21.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.21.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.21.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.21.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.22.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.22.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.22.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.22.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.22.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.22.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.23.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.23.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.23.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.23.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.23.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.23.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.24.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.24.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.24.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.24.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.24.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.24.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.25.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.25.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.25.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.25.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.25.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.25.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.26.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.26.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.26.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.26.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.26.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.26.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.27.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.27.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.27.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.27.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.27.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.27.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.28.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.28.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.28.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.28.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.28.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.28.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.29.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.29.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.29.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.29.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.29.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.29.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.3.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.3.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.3.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.30.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.30.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.30.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.30.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.30.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.30.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.31.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.31.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.31.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.31.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.31.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.31.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.32.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.32.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.32.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.32.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.32.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.32.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.33.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.33.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.33.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.33.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.33.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.33.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.34.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.34.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.34.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.34.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.34.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.34.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.35.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.35.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.35.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.35.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.35.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.35.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.36.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.36.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.36.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.36.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.36.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.36.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.37.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.37.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.37.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.37.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.37.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.37.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.38.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.38.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.38.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.38.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.38.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.38.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.39.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.39.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.39.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.39.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.39.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.39.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.4.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.4.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.4.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.40.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.40.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.40.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.40.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.40.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.40.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.41.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.41.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.41.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.41.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.41.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.41.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.42.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.42.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.42.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.42.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.42.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.42.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.43.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.43.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.43.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.43.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.43.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.43.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.44.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.44.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.44.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.44.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.44.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.44.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.45.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.45.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.45.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.45.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.45.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.45.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.46.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.46.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.46.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.46.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.46.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.46.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.47.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.47.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.47.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.47.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.47.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.47.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.48.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.48.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.48.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.48.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.48.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.48.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.49.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.49.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.49.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.49.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.49.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.49.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.5.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.5.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.5.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.5.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.5.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.5.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.50.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.50.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.50.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.50.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.50.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.50.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.51.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.51.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.51.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.51.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.51.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.51.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.52.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.52.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.52.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.52.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.52.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.52.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.53.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.53.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.53.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.53.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.53.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.53.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.54.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.54.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.54.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.54.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.54.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.54.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.55.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.55.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.55.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.55.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.55.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.55.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.56.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.56.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.56.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.56.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.56.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.56.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.57.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.57.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.57.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.57.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.57.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.57.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.58.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.58.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.58.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.58.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.58.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.58.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.59.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.59.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.59.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.59.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.59.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.59.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.6.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.6.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.6.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.6.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.6.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.6.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.60.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.60.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.60.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.60.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.60.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.60.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.61.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.61.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.61.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.61.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.61.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.61.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.62.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.62.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.62.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.62.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.62.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.62.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.63.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.63.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.63.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.63.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.63.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.63.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.64.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.64.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.64.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.64.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.64.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.64.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.65.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.65.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.65.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.65.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.65.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.65.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.66.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.66.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.66.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.66.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.66.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.66.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.67.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.67.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.67.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.67.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.67.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.67.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.68.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.68.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.68.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.68.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.68.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.68.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.69.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.69.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.69.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.69.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.69.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.69.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.7.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.7.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.7.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.7.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.7.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.7.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.70.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.70.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.70.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.70.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.70.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.70.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.71.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.71.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.71.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.71.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.71.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.71.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.72.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.72.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.72.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.72.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.72.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.72.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.73.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.73.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.73.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.73.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.73.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.73.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.74.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.74.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.74.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.74.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.74.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.74.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.75.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.75.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.75.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.75.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.75.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.75.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.76.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.76.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.76.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.76.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.76.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.76.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.77.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.77.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.77.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.77.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.77.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.77.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.78.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.78.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.78.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.78.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.78.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.78.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.79.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.79.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.79.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.79.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.79.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.79.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.8.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.8.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.8.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.8.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.8.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.8.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.80.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.80.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.80.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.80.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.80.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.80.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.81.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.81.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.81.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.81.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.81.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.81.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.82.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.82.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.82.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.82.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.82.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.82.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.83.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.83.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.83.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.83.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.83.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.83.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.84.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.84.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.84.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.84.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.84.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.84.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.85.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.85.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.85.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.85.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.85.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.85.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.86.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.86.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.86.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.86.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.86.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.86.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.87.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.87.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.87.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.87.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.87.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.87.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.88.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.88.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.88.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.88.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.88.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.88.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.89.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.89.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.89.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.89.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.89.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.89.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.9.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.9.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.9.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.9.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.9.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.9.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.90.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.90.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.90.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.90.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.90.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.90.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.91.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.91.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.91.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.91.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.91.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.91.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.92.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.92.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.92.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.92.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.92.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.92.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.93.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.93.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.93.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.93.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.93.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.93.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.94.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.94.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.94.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.94.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.94.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.94.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.95.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.95.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.95.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.95.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.95.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.95.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.96.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.96.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.96.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.96.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.96.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.96.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.97.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.97.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.97.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.97.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.97.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.97.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.98.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.98.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.98.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.98.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.98.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.98.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.99.w1.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.99.w1.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.99.w2.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.99.w2.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.99.w3.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.experts.99.w3.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.shared_experts.down_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.shared_experts.gate_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.shared_experts.up_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.input_layernorm.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.post_attention_layernorm.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.index_k_norm.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.index_k_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.index_q_norm.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.index_q_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.k_norm.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.k_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.k_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.o_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.o_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.q_norm.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.q_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.q_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.v_proj.weight": "model-00043-of-00059.safetensors", - "language_model.model.layers.43.self_attn.v_proj.weight_scale": "model-00043-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.gate.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.108.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.108.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.108.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.108.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.108.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.108.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.109.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.109.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.109.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.109.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.109.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.109.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.11.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.11.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.11.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.11.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.11.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.11.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.110.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.110.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.110.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.110.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.110.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.110.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.111.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.111.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.111.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.111.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.111.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.111.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.112.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.112.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.112.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.112.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.112.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.112.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.113.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.113.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.113.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.113.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.113.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.113.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.114.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.114.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.114.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.114.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.114.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.114.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.115.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.115.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.115.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.115.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.115.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.115.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.116.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.116.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.116.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.116.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.116.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.116.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.117.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.117.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.117.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.117.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.117.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.117.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.118.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.118.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.118.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.118.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.118.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.118.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.119.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.119.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.119.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.119.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.119.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.119.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.12.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.12.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.12.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.12.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.12.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.12.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.120.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.120.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.120.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.120.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.120.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.120.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.121.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.121.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.121.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.121.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.121.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.121.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.122.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.122.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.122.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.122.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.122.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.122.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.123.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.123.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.123.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.123.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.123.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.123.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.124.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.124.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.124.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.124.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.124.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.124.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.125.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.125.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.125.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.125.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.125.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.125.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.126.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.126.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.126.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.126.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.126.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.126.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.127.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.127.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.127.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.127.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.127.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.127.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.13.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.13.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.13.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.13.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.13.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.13.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.14.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.14.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.14.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.14.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.14.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.14.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.15.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.15.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.15.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.15.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.15.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.15.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.16.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.16.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.16.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.16.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.16.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.16.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.17.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.17.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.17.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.17.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.17.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.17.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.18.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.18.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.18.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.18.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.18.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.18.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.19.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.19.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.19.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.19.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.19.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.19.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.2.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.2.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.2.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.20.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.20.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.20.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.20.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.20.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.20.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.21.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.21.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.21.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.21.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.21.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.21.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.22.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.22.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.22.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.22.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.22.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.22.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.23.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.23.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.23.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.23.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.23.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.23.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.24.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.24.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.24.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.24.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.24.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.24.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.25.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.25.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.25.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.25.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.25.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.25.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.26.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.26.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.26.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.26.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.26.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.26.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.27.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.27.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.27.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.27.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.27.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.27.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.28.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.28.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.28.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.28.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.28.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.28.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.29.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.29.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.29.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.29.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.29.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.29.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.3.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.3.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.3.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.30.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.30.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.30.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.30.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.30.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.30.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.31.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.31.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.31.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.31.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.31.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.31.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.32.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.32.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.32.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.32.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.32.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.32.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.33.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.33.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.33.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.33.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.33.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.33.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.34.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.34.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.34.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.34.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.34.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.34.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.35.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.35.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.35.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.35.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.35.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.35.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.36.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.36.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.36.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.36.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.36.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.36.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.37.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.37.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.37.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.37.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.37.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.37.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.38.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.38.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.38.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.38.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.38.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.38.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.39.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.39.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.39.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.39.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.39.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.39.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.4.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.4.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.4.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.40.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.40.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.40.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.40.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.40.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.40.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.41.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.41.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.41.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.41.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.41.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.41.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.42.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.42.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.42.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.42.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.42.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.42.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.43.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.43.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.43.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.43.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.43.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.43.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.44.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.44.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.44.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.44.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.44.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.44.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.45.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.45.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.45.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.45.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.45.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.45.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.46.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.46.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.46.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.46.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.46.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.46.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.47.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.47.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.47.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.47.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.47.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.47.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.48.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.48.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.48.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.48.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.48.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.48.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.49.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.49.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.49.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.49.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.49.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.49.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.5.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.5.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.5.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.50.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.50.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.50.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.50.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.50.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.50.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.51.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.51.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.51.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.51.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.51.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.51.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.52.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.52.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.52.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.52.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.52.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.52.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.53.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.53.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.53.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.53.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.53.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.53.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.54.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.54.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.54.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.54.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.54.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.54.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.55.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.55.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.55.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.55.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.55.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.55.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.56.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.56.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.56.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.56.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.56.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.56.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.57.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.57.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.57.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.57.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.57.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.57.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.58.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.58.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.58.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.58.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.58.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.58.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.59.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.59.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.59.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.59.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.59.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.59.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.6.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.6.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.6.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.60.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.60.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.60.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.60.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.60.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.60.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.61.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.61.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.61.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.61.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.61.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.61.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.62.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.62.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.62.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.62.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.62.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.62.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.63.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.63.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.63.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.63.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.63.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.63.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.64.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.64.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.64.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.64.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.64.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.64.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.65.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.65.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.65.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.65.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.65.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.65.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.66.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.66.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.66.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.66.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.66.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.66.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.67.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.67.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.67.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.67.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.67.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.67.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.68.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.68.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.68.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.68.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.68.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.68.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.69.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.69.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.69.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.69.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.69.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.69.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.7.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.7.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.7.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.70.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.70.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.70.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.70.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.70.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.70.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.71.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.71.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.71.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.71.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.71.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.71.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.72.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.72.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.72.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.72.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.72.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.72.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.73.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.73.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.73.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.73.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.73.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.73.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.74.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.74.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.74.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.74.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.74.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.74.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.75.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.75.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.75.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.75.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.75.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.75.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.76.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.76.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.76.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.76.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.76.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.76.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.77.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.77.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.77.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.77.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.77.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.77.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.78.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.78.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.78.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.78.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.78.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.78.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.79.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.79.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.79.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.79.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.79.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.79.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.8.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.8.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.8.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.8.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.8.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.8.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.80.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.80.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.80.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.80.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.80.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.80.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.81.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.81.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.81.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.81.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.81.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.81.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.82.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.82.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.82.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.82.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.82.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.82.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.83.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.83.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.83.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.83.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.83.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.83.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.84.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.84.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.84.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.84.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.84.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.84.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.85.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.85.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.85.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.85.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.85.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.85.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.86.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.86.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.86.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.86.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.86.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.86.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.87.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.87.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.87.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.87.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.87.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.87.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.88.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.88.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.88.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.88.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.88.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.88.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.89.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.89.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.89.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.89.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.89.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.89.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.9.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.9.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.9.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.9.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.9.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.9.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.90.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.90.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.90.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.90.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.90.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.90.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.91.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.91.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.91.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.91.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.91.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.91.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.92.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.92.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.92.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.92.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.92.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.92.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.93.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.93.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.93.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.93.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.93.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.93.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.94.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.94.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.94.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.94.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.94.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.94.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.95.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.95.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.95.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.95.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.95.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.95.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.96.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.96.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.96.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.96.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.96.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.96.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.97.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.97.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.97.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.97.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.97.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.97.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.98.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.98.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.98.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.98.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.98.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.98.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.99.w1.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.99.w1.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.99.w2.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.99.w2.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.99.w3.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.experts.99.w3.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.shared_experts.down_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.shared_experts.gate_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.shared_experts.up_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.input_layernorm.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.post_attention_layernorm.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.index_k_norm.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.index_k_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.index_q_norm.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.index_q_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.k_norm.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.k_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.k_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.o_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.o_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.q_norm.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.q_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.q_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.v_proj.weight": "model-00037-of-00059.safetensors", - "language_model.model.layers.37.self_attn.v_proj.weight_scale": "model-00037-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.e_score_correction_bias": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.gate.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.0.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.0.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.0.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.1.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.1.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.1.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.10.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.10.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.10.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.10.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.10.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.10.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.100.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.100.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.100.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.100.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.100.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.100.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.101.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.101.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.101.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.101.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.101.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.101.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.102.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.102.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.102.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.102.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.102.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.102.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.103.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.103.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.103.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.103.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.103.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.103.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.104.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.104.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.104.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.104.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.104.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.104.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.105.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.105.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.105.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.105.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.105.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.105.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.106.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.106.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.106.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.106.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.106.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.106.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.107.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.107.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.107.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.107.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.107.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.107.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.108.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.108.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.108.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.108.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.108.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.108.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.109.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.109.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.109.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.109.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.109.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.109.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.11.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.11.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.11.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.11.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.11.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.11.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.110.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.110.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.110.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.110.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.110.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.110.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.111.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.111.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.111.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.111.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.111.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.111.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.112.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.112.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.112.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.112.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.112.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.112.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.113.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.113.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.113.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.113.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.113.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.113.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.114.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.114.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.114.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.114.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.114.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.114.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.115.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.115.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.115.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.115.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.115.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.115.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.116.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.116.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.116.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.116.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.116.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.116.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.117.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.117.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.117.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.117.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.117.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.117.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.118.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.118.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.118.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.118.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.118.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.118.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.119.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.119.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.119.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.119.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.119.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.119.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.12.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.12.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.12.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.12.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.12.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.12.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.120.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.120.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.120.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.120.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.120.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.120.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.121.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.121.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.121.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.121.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.121.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.121.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.122.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.122.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.122.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.122.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.122.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.122.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.123.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.123.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.123.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.123.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.123.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.123.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.124.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.124.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.124.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.124.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.124.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.124.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.125.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.125.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.125.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.125.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.125.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.125.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.126.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.126.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.126.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.126.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.126.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.126.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.127.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.127.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.127.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.127.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.127.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.127.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.13.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.13.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.13.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.13.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.13.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.13.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.14.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.14.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.14.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.14.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.14.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.14.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.15.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.15.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.15.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.15.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.15.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.15.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.16.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.16.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.16.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.16.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.16.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.16.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.17.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.17.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.17.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.17.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.17.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.17.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.18.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.18.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.18.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.18.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.18.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.18.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.19.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.19.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.19.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.19.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.19.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.19.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.2.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.2.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.2.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.20.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.20.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.20.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.20.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.20.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.20.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.21.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.21.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.21.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.21.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.21.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.21.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.22.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.22.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.22.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.22.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.22.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.22.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.23.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.23.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.23.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.23.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.23.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.23.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.24.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.24.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.24.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.24.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.24.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.24.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.25.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.25.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.25.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.25.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.25.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.25.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.26.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.26.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.26.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.26.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.26.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.26.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.27.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.27.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.27.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.27.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.27.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.27.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.28.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.28.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.28.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.28.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.28.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.28.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.29.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.29.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.29.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.29.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.29.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.29.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.3.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.3.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.3.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.30.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.30.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.30.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.30.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.30.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.30.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.31.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.31.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.31.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.31.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.31.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.31.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.32.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.32.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.32.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.32.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.32.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.32.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.33.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.33.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.33.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.33.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.33.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.33.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.34.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.34.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.34.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.34.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.34.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.34.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.35.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.35.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.35.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.35.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.35.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.35.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.36.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.36.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.36.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.36.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.36.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.36.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.37.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.37.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.37.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.37.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.37.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.37.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.38.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.38.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.38.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.38.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.38.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.38.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.39.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.39.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.39.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.39.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.39.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.39.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.4.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.4.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.4.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.40.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.40.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.40.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.40.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.40.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.40.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.41.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.41.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.41.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.41.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.41.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.41.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.42.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.42.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.42.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.42.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.42.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.42.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.43.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.43.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.43.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.43.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.43.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.43.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.44.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.44.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.44.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.44.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.44.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.44.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.45.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.45.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.45.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.45.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.45.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.45.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.46.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.46.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.46.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.46.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.46.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.46.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.47.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.47.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.47.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.47.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.47.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.47.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.48.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.48.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.48.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.48.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.48.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.48.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.49.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.49.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.49.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.49.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.49.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.49.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.5.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.5.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.5.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.50.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.50.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.50.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.50.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.50.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.50.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.51.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.51.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.51.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.51.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.51.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.51.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.52.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.52.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.52.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.52.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.52.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.52.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.53.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.53.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.53.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.53.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.53.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.53.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.54.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.54.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.54.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.54.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.54.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.54.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.55.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.55.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.55.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.55.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.55.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.55.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.56.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.56.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.56.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.56.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.56.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.56.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.57.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.57.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.57.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.57.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.57.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.57.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.58.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.58.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.58.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.58.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.58.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.58.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.59.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.59.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.59.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.59.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.59.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.59.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.6.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.6.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.6.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.60.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.60.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.60.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.60.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.60.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.60.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.61.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.61.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.61.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.61.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.61.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.61.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.62.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.62.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.62.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.62.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.62.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.62.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.63.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.63.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.63.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.63.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.63.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.63.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.64.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.64.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.64.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.64.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.64.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.64.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.65.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.65.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.65.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.65.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.65.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.65.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.66.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.66.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.66.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.66.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.66.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.66.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.67.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.67.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.67.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.67.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.67.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.67.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.68.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.68.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.68.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.68.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.68.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.68.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.69.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.69.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.69.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.69.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.69.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.69.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.7.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.7.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.7.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.70.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.70.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.70.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.70.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.70.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.70.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.71.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.71.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.71.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.71.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.71.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.71.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.72.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.72.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.72.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.72.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.72.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.72.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.73.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.73.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.73.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.73.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.73.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.73.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.74.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.74.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.74.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.74.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.74.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.74.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.75.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.75.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.75.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.75.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.75.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.75.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.76.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.76.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.76.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.76.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.76.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.76.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.77.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.77.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.77.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.77.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.77.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.77.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.78.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.78.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.78.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.78.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.78.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.78.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.79.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.79.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.79.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.79.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.79.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.79.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.8.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.8.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.8.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.8.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.8.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.8.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.80.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.80.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.80.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.80.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.80.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.80.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.81.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.81.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.81.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.81.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.81.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.81.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.82.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.82.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.82.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.82.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.82.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.82.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.83.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.83.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.83.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.83.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.83.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.83.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.84.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.84.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.84.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.84.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.84.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.84.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.85.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.85.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.85.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.85.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.85.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.85.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.86.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.86.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.86.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.86.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.86.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.86.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.87.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.87.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.87.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.87.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.87.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.87.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.88.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.88.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.88.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.88.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.88.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.88.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.89.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.89.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.89.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.89.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.89.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.89.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.9.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.9.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.9.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.9.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.9.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.9.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.90.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.90.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.90.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.90.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.90.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.90.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.91.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.91.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.91.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.91.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.91.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.91.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.92.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.92.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.92.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.92.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.92.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.92.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.93.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.93.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.93.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.93.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.93.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.93.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.94.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.94.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.94.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.94.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.94.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.94.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.95.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.95.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.95.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.95.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.95.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.95.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.96.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.96.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.96.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.96.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.96.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.96.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.97.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.97.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.97.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.97.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.97.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.97.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.98.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.98.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.98.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.98.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.98.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.98.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.99.w1.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.99.w1.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.99.w2.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.99.w2.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.99.w3.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.experts.99.w3.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.shared_experts.down_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.shared_experts.gate_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.shared_experts.up_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.input_layernorm.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.post_attention_layernorm.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.index_k_norm.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.index_k_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.index_q_norm.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.index_q_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.k_norm.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.k_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.k_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.o_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.o_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.q_norm.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.q_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.q_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.v_proj.weight": "model-00028-of-00059.safetensors", - "language_model.model.layers.28.self_attn.v_proj.weight_scale": "model-00028-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.e_score_correction_bias": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.gate.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.e_score_correction_bias": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.0.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.0.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.0.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.1.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.1.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.1.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.10.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.10.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.10.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.10.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.10.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.10.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.100.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.100.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.100.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.100.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.100.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.100.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.101.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.101.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.101.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.101.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.101.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.101.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.102.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.102.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.102.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.102.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.102.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.102.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.103.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.103.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.103.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.103.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.103.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.103.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.104.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.104.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.104.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.104.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.104.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.104.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.105.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.105.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.105.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.105.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.105.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.105.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.106.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.106.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.106.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.106.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.106.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.106.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.107.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.107.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.107.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.107.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.107.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.107.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.108.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.108.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.108.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.108.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.108.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.108.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.109.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.109.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.109.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.109.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.109.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.109.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.11.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.11.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.11.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.11.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.11.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.11.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.110.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.110.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.110.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.110.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.110.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.110.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.111.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.111.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.111.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.111.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.111.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.111.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.112.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.112.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.112.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.112.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.112.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.112.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.113.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.113.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.113.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.113.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.113.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.113.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.114.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.114.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.114.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.114.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.114.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.114.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.115.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.115.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.115.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.115.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.115.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.115.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.116.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.116.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.116.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.116.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.116.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.116.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.117.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.117.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.117.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.117.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.117.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.117.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.118.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.118.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.118.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.118.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.118.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.118.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.119.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.119.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.119.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.119.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.119.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.119.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.12.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.12.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.12.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.12.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.12.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.12.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.120.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.120.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.120.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.120.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.120.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.120.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.121.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.121.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.121.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.121.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.121.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.121.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.122.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.122.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.122.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.122.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.122.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.122.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.123.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.123.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.123.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.123.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.123.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.123.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.124.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.124.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.124.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.124.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.124.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.124.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.125.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.125.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.125.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.125.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.125.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.125.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.126.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.126.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.126.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.126.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.126.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.126.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.127.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.127.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.127.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.127.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.127.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.127.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.13.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.13.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.13.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.13.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.13.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.13.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.14.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.14.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.14.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.14.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.14.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.14.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.15.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.15.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.15.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.15.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.15.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.15.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.16.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.16.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.16.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.16.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.16.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.16.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.17.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.17.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.17.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.17.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.17.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.17.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.18.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.18.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.18.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.18.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.18.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.18.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.19.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.19.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.19.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.19.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.19.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.19.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.2.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.2.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.2.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.20.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.20.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.20.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.20.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.20.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.20.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.21.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.21.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.21.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.21.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.21.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.21.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.22.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.22.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.22.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.22.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.22.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.22.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.23.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.23.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.23.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.23.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.23.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.23.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.24.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.24.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.24.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.24.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.24.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.24.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.25.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.25.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.25.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.25.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.25.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.25.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.26.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.26.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.26.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.26.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.26.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.26.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.27.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.27.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.27.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.27.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.27.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.27.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.28.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.28.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.28.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.28.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.28.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.28.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.29.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.29.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.29.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.29.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.29.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.29.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.3.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.3.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.3.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.30.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.30.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.30.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.30.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.30.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.30.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.31.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.31.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.31.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.31.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.31.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.31.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.32.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.32.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.32.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.32.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.32.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.32.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.33.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.33.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.33.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.33.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.33.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.33.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.34.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.34.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.34.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.34.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.34.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.34.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.35.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.35.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.35.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.35.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.35.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.35.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.36.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.36.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.36.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.36.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.36.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.36.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.37.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.37.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.37.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.37.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.37.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.37.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.38.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.38.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.38.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.38.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.38.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.38.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.39.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.39.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.39.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.39.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.39.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.39.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.4.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.4.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.4.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.40.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.40.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.40.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.40.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.40.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.40.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.41.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.41.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.41.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.41.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.41.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.41.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.42.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.42.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.42.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.42.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.42.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.42.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.43.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.43.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.43.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.43.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.43.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.43.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.44.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.44.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.44.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.44.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.44.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.44.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.45.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.45.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.45.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.45.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.45.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.45.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.46.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.46.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.46.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.46.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.46.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.46.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.47.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.47.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.47.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.47.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.47.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.47.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.48.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.48.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.48.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.48.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.48.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.48.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.49.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.49.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.49.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.49.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.49.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.49.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.5.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.5.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.5.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.50.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.50.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.50.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.50.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.50.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.50.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.51.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.51.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.51.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.51.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.51.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.51.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.52.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.52.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.52.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.52.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.52.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.52.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.53.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.53.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.53.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.53.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.53.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.53.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.54.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.54.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.54.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.54.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.54.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.54.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.55.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.55.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.55.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.55.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.55.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.55.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.56.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.56.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.56.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.56.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.56.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.56.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.57.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.57.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.57.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.57.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.57.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.57.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.58.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.58.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.58.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.58.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.58.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.58.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.59.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.59.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.59.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.59.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.59.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.59.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.6.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.6.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.6.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.60.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.60.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.60.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.60.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.60.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.60.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.61.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.61.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.61.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.61.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.61.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.61.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.62.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.62.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.62.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.62.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.62.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.62.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.63.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.63.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.63.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.63.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.63.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.63.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.64.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.64.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.64.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.64.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.64.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.64.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.65.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.65.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.65.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.65.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.65.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.65.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.66.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.66.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.66.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.66.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.66.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.66.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.67.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.67.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.67.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.67.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.67.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.67.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.68.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.68.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.68.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.68.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.68.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.68.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.69.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.69.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.69.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.69.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.69.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.69.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.7.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.7.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.7.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.70.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.70.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.70.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.70.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.70.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.70.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.71.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.71.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.71.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.71.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.71.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.71.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.72.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.72.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.72.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.72.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.72.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.72.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.73.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.73.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.73.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.73.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.73.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.73.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.74.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.74.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.74.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.74.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.74.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.74.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.75.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.75.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.75.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.75.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.75.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.75.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.76.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.76.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.76.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.76.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.76.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.76.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.77.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.77.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.77.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.77.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.77.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.77.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.78.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.78.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.78.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.78.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.78.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.78.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.79.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.79.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.79.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.79.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.79.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.79.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.8.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.8.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.8.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.8.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.8.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.8.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.80.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.80.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.80.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.80.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.80.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.80.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.81.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.81.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.81.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.81.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.81.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.81.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.82.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.82.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.82.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.82.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.82.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.82.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.83.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.83.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.83.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.83.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.83.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.83.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.84.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.84.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.84.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.84.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.84.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.84.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.85.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.85.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.85.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.85.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.85.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.85.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.86.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.86.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.86.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.86.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.86.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.86.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.87.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.87.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.87.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.87.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.87.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.87.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.88.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.88.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.88.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.88.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.88.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.88.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.89.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.89.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.89.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.89.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.89.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.89.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.9.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.9.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.9.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.9.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.9.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.9.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.90.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.90.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.90.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.90.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.90.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.90.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.91.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.91.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.91.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.91.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.91.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.91.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.92.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.92.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.92.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.92.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.92.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.92.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.93.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.93.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.93.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.93.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.93.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.93.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.94.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.94.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.94.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.94.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.94.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.94.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.95.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.95.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.95.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.95.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.95.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.95.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.96.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.96.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.96.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.96.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.96.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.96.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.97.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.97.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.97.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.97.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.97.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.97.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.98.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.98.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.98.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.98.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.98.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.98.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.99.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.99.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.99.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.99.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.99.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.experts.99.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.shared_experts.down_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.shared_experts.gate_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.shared_experts.up_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.input_layernorm.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.post_attention_layernorm.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.index_k_norm.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.index_k_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.index_q_norm.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.index_q_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.k_norm.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.k_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.k_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.o_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.o_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.q_norm.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.q_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.q_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.v_proj.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.24.self_attn.v_proj.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.0.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.0.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.0.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.1.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.1.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.1.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.10.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.10.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.10.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.10.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.10.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.10.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.100.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.100.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.100.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.100.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.100.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.100.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.101.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.101.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.101.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.101.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.101.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.101.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.102.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.102.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.102.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.102.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.102.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.102.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.103.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.103.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.103.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.103.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.103.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.103.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.104.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.104.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.104.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.104.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.104.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.104.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.105.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.105.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.105.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.105.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.105.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.105.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.106.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.106.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.106.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.106.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.106.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.106.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.107.w1.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.107.w1.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.107.w2.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.107.w2.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.107.w3.weight": "model-00024-of-00059.safetensors", - "language_model.model.layers.58.block_sparse_moe.experts.107.w3.weight_scale": "model-00024-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.e_score_correction_bias": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.gate.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.e_score_correction_bias": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.0.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.0.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.0.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.1.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.1.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.1.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.10.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.10.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.10.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.100.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.100.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.100.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.101.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.101.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.101.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.102.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.102.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.102.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.103.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.103.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.103.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.104.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.104.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.104.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.105.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.105.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.105.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.106.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.106.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.106.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.107.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.107.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.107.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.108.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.108.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.108.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.108.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.108.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.108.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.109.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.109.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.109.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.109.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.109.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.109.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.11.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.11.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.11.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.110.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.110.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.110.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.110.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.110.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.110.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.111.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.111.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.111.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.111.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.111.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.111.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.112.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.112.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.112.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.112.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.112.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.112.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.113.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.113.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.113.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.113.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.113.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.113.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.114.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.114.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.114.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.114.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.114.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.114.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.115.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.115.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.115.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.115.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.115.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.115.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.116.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.116.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.116.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.116.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.116.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.116.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.117.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.117.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.117.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.117.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.117.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.117.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.118.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.118.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.118.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.118.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.118.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.118.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.119.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.119.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.119.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.119.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.119.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.119.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.12.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.12.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.12.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.120.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.120.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.120.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.120.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.120.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.120.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.121.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.121.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.121.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.121.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.121.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.121.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.122.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.122.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.122.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.122.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.122.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.122.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.123.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.123.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.123.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.123.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.123.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.123.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.124.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.124.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.124.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.124.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.124.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.124.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.125.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.125.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.125.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.125.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.125.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.125.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.126.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.126.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.126.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.126.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.126.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.126.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.127.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.127.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.127.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.127.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.127.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.127.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.13.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.13.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.13.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.14.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.14.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.14.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.15.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.15.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.15.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.16.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.16.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.16.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.17.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.17.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.17.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.18.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.18.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.18.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.19.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.19.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.19.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.2.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.2.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.2.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.20.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.20.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.20.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.21.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.21.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.21.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.22.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.22.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.22.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.23.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.23.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.23.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.24.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.24.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.24.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.25.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.25.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.25.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.26.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.26.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.26.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.27.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.27.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.27.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.28.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.28.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.28.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.29.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.29.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.29.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.3.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.3.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.3.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.30.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.30.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.30.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.31.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.31.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.31.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.32.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.32.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.32.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.32.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.32.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.32.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.33.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.33.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.33.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.33.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.33.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.33.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.34.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.34.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.34.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.34.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.34.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.34.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.35.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.35.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.35.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.35.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.35.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.35.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.36.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.36.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.36.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.36.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.36.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.36.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.37.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.37.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.37.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.37.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.37.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.37.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.38.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.38.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.38.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.38.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.38.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.38.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.39.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.39.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.39.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.39.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.39.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.39.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.4.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.4.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.4.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.40.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.40.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.40.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.40.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.40.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.40.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.41.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.41.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.41.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.41.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.41.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.41.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.42.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.42.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.42.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.42.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.42.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.42.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.43.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.43.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.43.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.43.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.43.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.43.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.44.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.44.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.44.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.44.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.44.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.44.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.45.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.45.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.45.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.45.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.45.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.45.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.46.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.46.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.46.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.46.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.46.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.46.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.47.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.47.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.47.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.47.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.47.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.47.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.48.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.48.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.48.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.48.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.48.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.48.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.49.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.49.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.49.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.49.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.49.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.49.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.5.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.5.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.5.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.50.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.50.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.50.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.50.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.50.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.50.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.51.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.51.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.51.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.51.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.51.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.51.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.52.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.52.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.52.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.52.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.52.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.52.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.53.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.53.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.53.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.53.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.53.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.53.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.54.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.54.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.54.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.54.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.54.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.54.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.55.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.55.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.55.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.55.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.55.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.55.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.56.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.56.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.56.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.56.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.56.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.56.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.57.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.57.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.57.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.57.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.57.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.57.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.58.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.58.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.58.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.58.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.58.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.58.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.59.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.59.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.59.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.59.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.59.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.59.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.6.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.6.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.6.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.60.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.60.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.60.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.60.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.60.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.60.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.61.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.61.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.61.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.61.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.61.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.61.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.62.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.62.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.62.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.62.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.62.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.62.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.63.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.63.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.63.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.63.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.63.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.63.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.64.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.64.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.64.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.64.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.64.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.64.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.65.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.65.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.65.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.65.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.65.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.65.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.66.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.66.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.66.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.66.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.66.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.66.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.67.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.67.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.67.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.67.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.67.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.67.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.68.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.68.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.68.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.68.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.68.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.68.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.69.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.69.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.69.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.69.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.69.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.69.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.7.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.7.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.7.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.70.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.70.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.70.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.70.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.70.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.70.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.71.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.71.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.71.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.71.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.71.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.71.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.72.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.72.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.72.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.72.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.72.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.72.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.73.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.73.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.73.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.73.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.73.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.73.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.74.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.74.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.74.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.74.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.74.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.74.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.75.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.75.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.75.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.75.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.75.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.75.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.76.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.76.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.76.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.76.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.76.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.76.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.77.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.77.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.77.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.77.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.77.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.77.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.78.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.78.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.78.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.78.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.78.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.78.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.79.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.79.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.79.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.79.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.79.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.79.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.8.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.8.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.8.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.80.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.80.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.80.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.80.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.80.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.80.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.81.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.81.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.81.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.81.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.81.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.81.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.82.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.82.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.82.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.82.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.82.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.83.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.83.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.83.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.84.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.84.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.84.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.85.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.85.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.85.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.86.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.86.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.86.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.87.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.87.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.87.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.88.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.88.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.88.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.88.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.88.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.89.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.89.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.89.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.89.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.89.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.89.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.9.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.9.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.9.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.90.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.90.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.90.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.90.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.90.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.90.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.91.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.91.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.91.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.91.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.91.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.91.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.92.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.92.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.92.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.92.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.92.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.92.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.93.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.93.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.93.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.93.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.93.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.93.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.94.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.94.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.94.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.94.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.94.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.94.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.95.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.95.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.95.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.95.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.95.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.95.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.96.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.96.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.96.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.96.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.96.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.96.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.97.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.97.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.97.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.97.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.97.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.97.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.98.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.98.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.98.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.98.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.98.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.98.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.99.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.99.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.99.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.99.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.99.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.experts.99.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.shared_experts.down_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.shared_experts.gate_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.shared_experts.up_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.input_layernorm.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.post_attention_layernorm.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.index_k_norm.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.index_k_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.index_q_norm.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.index_q_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.k_norm.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.k_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.k_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.o_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.o_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.q_norm.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.q_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.q_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.v_proj.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.15.self_attn.v_proj.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.0.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.0.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.0.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.1.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.1.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.1.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.10.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.10.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.10.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.100.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.100.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.100.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.101.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.101.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.101.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.102.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.102.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.102.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.103.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.103.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.103.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.104.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.104.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.104.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.105.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.105.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.105.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.106.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.106.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.106.w3.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.107.w1.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.107.w2.weight_scale": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00059.safetensors", - "language_model.model.layers.49.block_sparse_moe.experts.107.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.e_score_correction_bias": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.e_score_correction_bias": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.0.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.0.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.0.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.1.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.1.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.1.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.10.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.10.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.10.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.100.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.100.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.100.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.101.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.101.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.101.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.102.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.102.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.102.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.103.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.103.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.103.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.104.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.104.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.104.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.105.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.105.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.105.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.106.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.106.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.106.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.107.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.107.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.107.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.0.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.0.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.0.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.1.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.1.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.1.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.10.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.10.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.10.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.100.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.100.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.100.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.101.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.101.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.101.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.102.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.102.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.102.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.103.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.103.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.103.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.104.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.104.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.104.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.105.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.105.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.105.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.106.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.106.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.106.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.107.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.107.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.107.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.108.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.108.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.108.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.109.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.109.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.109.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.11.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.11.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.11.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.110.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.110.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.110.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.111.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.111.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.111.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.112.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.112.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.112.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.113.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.113.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.113.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.114.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.114.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.114.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.114.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.114.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.115.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.115.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.115.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.115.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.115.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.115.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.116.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.116.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.116.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.116.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.116.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.116.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.117.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.117.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.117.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.117.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.117.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.117.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.118.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.118.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.118.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.118.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.118.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.118.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.119.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.119.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.119.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.119.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.119.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.119.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.12.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.12.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.12.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.120.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.120.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.120.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.120.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.120.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.120.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.121.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.121.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.121.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.121.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.121.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.121.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.122.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.122.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.122.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.122.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.122.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.122.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.123.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.123.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.123.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.123.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.123.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.123.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.124.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.124.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.124.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.124.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.124.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.124.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.125.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.125.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.125.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.125.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.125.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.125.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.126.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.126.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.126.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.126.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.126.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.126.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.127.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.127.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.127.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.127.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.127.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.127.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.13.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.13.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.13.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.14.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.14.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.14.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.15.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.15.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.15.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.16.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.16.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.16.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.17.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.17.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.17.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.18.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.18.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.18.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.19.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.19.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.19.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.2.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.2.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.2.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.20.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.20.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.20.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.21.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.21.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.21.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.22.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.22.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.22.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.23.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.23.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.23.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.24.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.24.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.24.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.25.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.25.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.25.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.26.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.26.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.26.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.27.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.27.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.27.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.28.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.28.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.28.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.29.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.29.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.29.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.3.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.3.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.3.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.30.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.30.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.30.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.31.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.31.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.31.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.32.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.32.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.32.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.33.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.33.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.33.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.34.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.34.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.34.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.35.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.35.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.35.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.36.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.36.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.36.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.37.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.37.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.37.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.38.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.38.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.38.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.39.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.39.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.39.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.4.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.4.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.4.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.40.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.40.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.40.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.41.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.41.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.41.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.41.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.42.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.42.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.42.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.43.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.43.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.43.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.44.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.44.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.44.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.45.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.45.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.45.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.46.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.46.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.46.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.47.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.47.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.47.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.48.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.48.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.48.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.49.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.49.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.49.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.5.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.5.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.5.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.50.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.50.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.50.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.51.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.51.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.51.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.52.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.52.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.52.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.53.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.53.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.53.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.54.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.54.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.54.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.55.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.55.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.55.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.56.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.56.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.56.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.57.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.57.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.57.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.58.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.58.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.58.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.59.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.59.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.59.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.6.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.6.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.6.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.60.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.60.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.60.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.61.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.61.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.61.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.62.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.62.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.62.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.63.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.63.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.63.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.64.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.64.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.64.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.64.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.64.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.64.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.65.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.65.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.65.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.65.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.65.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.65.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.66.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.66.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.66.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.66.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.66.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.66.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.67.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.67.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.67.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.67.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.67.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.67.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.68.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.68.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.68.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.68.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.68.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.68.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.69.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.69.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.69.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.69.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.69.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.69.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.7.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.7.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.7.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.70.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.70.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.70.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.70.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.70.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.70.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.71.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.71.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.71.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.71.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.71.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.71.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.72.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.72.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.72.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.72.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.72.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.72.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.73.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.73.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.73.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.73.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.73.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.73.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.74.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.74.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.74.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.74.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.74.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.74.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.75.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.75.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.75.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.75.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.75.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.75.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.76.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.76.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.76.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.76.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.76.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.76.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.77.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.77.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.77.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.77.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.77.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.77.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.78.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.78.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.78.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.78.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.78.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.78.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.79.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.79.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.79.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.79.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.79.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.79.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.8.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.8.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.8.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.80.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.80.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.80.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.80.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.80.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.80.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.81.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.81.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.81.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.81.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.81.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.81.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.82.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.82.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.82.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.82.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.82.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.82.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.83.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.83.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.83.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.83.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.83.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.83.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.84.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.84.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.84.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.84.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.84.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.84.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.85.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.85.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.85.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.85.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.85.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.85.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.86.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.86.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.86.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.86.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.86.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.86.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.87.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.87.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.87.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.87.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.87.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.87.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.88.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.88.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.88.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.88.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.88.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.88.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.89.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.89.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.89.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.89.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.89.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.89.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.9.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.9.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.9.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.90.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.90.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.90.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.90.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.90.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.90.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.91.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.91.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.91.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.91.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.91.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.91.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.92.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.92.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.92.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.92.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.92.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.92.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.93.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.93.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.93.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.93.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.93.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.93.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.94.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.94.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.94.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.94.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.94.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.94.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.95.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.95.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.95.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.95.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.95.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.95.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.96.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.96.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.96.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.96.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.96.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.96.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.97.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.97.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.97.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.97.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.97.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.97.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.98.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.98.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.98.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.98.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.98.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.98.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.99.w1.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.99.w1.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.99.w2.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.99.w2.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.99.w3.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.experts.99.w3.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.shared_experts.down_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.shared_experts.gate_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.shared_experts.up_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.index_k_norm.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.index_k_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.index_k_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.index_q_norm.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.index_q_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.index_q_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.k_norm.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.q_norm.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00005-of-00059.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight_scale": "model-00005-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.gate.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.108.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.108.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.108.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.108.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.108.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.108.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.109.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.109.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.109.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.109.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.109.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.109.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.11.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.11.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.11.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.11.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.11.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.11.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.110.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.110.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.110.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.110.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.110.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.110.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.111.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.111.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.111.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.111.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.111.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.111.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.112.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.112.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.112.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.112.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.112.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.112.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.113.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.113.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.113.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.113.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.113.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.113.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.114.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.114.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.114.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.114.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.114.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.114.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.115.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.115.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.115.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.115.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.115.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.115.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.116.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.116.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.116.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.116.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.116.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.116.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.117.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.117.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.117.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.117.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.117.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.117.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.118.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.118.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.118.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.118.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.118.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.118.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.119.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.119.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.119.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.119.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.119.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.119.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.12.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.12.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.12.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.12.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.12.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.12.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.120.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.120.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.120.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.120.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.120.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.120.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.121.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.121.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.121.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.121.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.121.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.121.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.122.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.122.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.122.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.122.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.122.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.122.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.123.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.123.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.123.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.123.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.123.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.123.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.124.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.124.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.124.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.124.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.124.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.124.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.125.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.125.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.125.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.125.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.125.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.125.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.126.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.126.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.126.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.126.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.126.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.126.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.127.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.127.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.127.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.127.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.127.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.127.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.13.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.13.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.13.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.13.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.13.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.13.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.14.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.14.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.14.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.14.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.14.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.14.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.15.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.15.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.15.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.15.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.15.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.15.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.16.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.16.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.16.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.16.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.16.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.16.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.17.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.17.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.17.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.17.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.17.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.17.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.18.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.18.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.18.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.18.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.18.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.18.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.19.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.19.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.19.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.19.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.19.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.19.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.2.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.2.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.2.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.20.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.20.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.20.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.20.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.20.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.20.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.21.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.21.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.21.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.21.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.21.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.21.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.22.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.22.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.22.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.22.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.22.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.22.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.23.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.23.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.23.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.23.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.23.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.23.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.24.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.24.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.24.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.24.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.24.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.24.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.25.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.25.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.25.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.25.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.25.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.25.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.26.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.26.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.26.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.26.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.26.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.26.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.27.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.27.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.27.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.27.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.27.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.27.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.28.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.28.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.28.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.28.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.28.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.28.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.29.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.29.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.29.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.29.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.29.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.29.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.3.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.3.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.3.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.3.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.3.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.3.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.30.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.30.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.30.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.30.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.30.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.30.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.31.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.31.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.31.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.31.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.31.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.31.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.32.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.32.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.32.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.32.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.32.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.32.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.33.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.33.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.33.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.33.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.33.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.33.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.34.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.34.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.34.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.34.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.34.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.34.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.35.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.35.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.35.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.35.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.35.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.35.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.36.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.36.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.36.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.36.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.36.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.36.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.37.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.37.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.37.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.37.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.37.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.37.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.38.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.38.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.38.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.38.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.38.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.38.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.39.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.39.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.39.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.39.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.39.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.39.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.4.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.4.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.4.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.4.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.4.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.4.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.40.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.40.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.40.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.40.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.40.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.40.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.41.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.41.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.41.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.41.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.41.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.41.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.42.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.42.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.42.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.42.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.42.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.42.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.43.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.43.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.43.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.43.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.43.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.43.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.44.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.44.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.44.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.44.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.44.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.44.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.45.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.45.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.45.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.45.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.45.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.45.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.46.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.46.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.46.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.46.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.46.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.46.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.47.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.47.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.47.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.47.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.47.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.47.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.48.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.48.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.48.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.48.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.48.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.48.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.49.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.49.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.49.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.49.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.49.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.49.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.5.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.5.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.5.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.5.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.5.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.5.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.50.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.50.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.50.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.50.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.50.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.50.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.51.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.51.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.51.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.51.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.51.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.51.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.52.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.52.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.52.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.52.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.52.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.52.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.53.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.53.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.53.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.53.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.53.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.53.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.54.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.54.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.54.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.54.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.54.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.54.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.55.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.55.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.55.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.55.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.55.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.55.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.56.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.56.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.56.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.56.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.56.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.56.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.57.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.57.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.57.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.57.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.57.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.57.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.58.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.58.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.58.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.58.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.58.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.58.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.59.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.59.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.59.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.59.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.59.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.59.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.6.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.6.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.6.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.6.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.6.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.6.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.60.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.60.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.60.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.60.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.60.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.60.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.61.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.61.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.61.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.61.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.61.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.61.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.62.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.62.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.62.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.62.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.62.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.62.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.63.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.63.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.63.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.63.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.63.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.63.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.64.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.64.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.64.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.64.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.64.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.64.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.65.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.65.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.65.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.65.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.65.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.65.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.66.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.66.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.66.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.66.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.66.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.66.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.67.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.67.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.67.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.67.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.67.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.67.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.68.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.68.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.68.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.68.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.68.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.68.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.69.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.69.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.69.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.69.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.69.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.69.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.7.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.7.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.7.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.7.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.7.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.7.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.70.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.70.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.70.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.70.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.70.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.70.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.71.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.71.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.71.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.71.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.71.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.71.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.72.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.72.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.72.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.72.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.72.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.72.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.73.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.73.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.73.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.73.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.73.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.73.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.74.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.74.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.74.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.74.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.74.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.74.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.75.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.75.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.75.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.75.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.75.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.75.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.76.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.76.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.76.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.76.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.76.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.76.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.77.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.77.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.77.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.77.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.77.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.77.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.78.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.78.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.78.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.78.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.78.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.78.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.79.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.79.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.79.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.79.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.79.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.79.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.8.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.8.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.8.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.8.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.8.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.8.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.80.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.80.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.80.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.80.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.80.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.80.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.81.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.81.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.81.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.81.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.81.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.81.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.82.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.82.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.82.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.82.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.82.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.82.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.83.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.83.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.83.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.83.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.83.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.83.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.84.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.84.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.84.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.84.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.84.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.84.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.85.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.85.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.85.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.85.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.85.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.85.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.86.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.86.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.86.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.86.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.86.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.86.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.87.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.87.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.87.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.87.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.87.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.87.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.88.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.88.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.88.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.88.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.88.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.88.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.89.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.89.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.89.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.89.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.89.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.89.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.9.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.9.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.9.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.9.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.9.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.9.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.90.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.90.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.90.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.90.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.90.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.90.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.91.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.91.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.91.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.91.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.91.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.91.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.92.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.92.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.92.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.92.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.92.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.92.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.93.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.93.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.93.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.93.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.93.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.93.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.94.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.94.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.94.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.94.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.94.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.94.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.95.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.95.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.95.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.95.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.95.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.95.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.96.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.96.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.96.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.96.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.96.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.96.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.97.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.97.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.97.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.97.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.97.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.97.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.98.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.98.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.98.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.98.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.98.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.98.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.99.w1.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.99.w1.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.99.w2.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.99.w2.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.99.w3.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.99.w3.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.shared_experts.down_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.shared_experts.gate_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.shared_experts.up_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.input_layernorm.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.post_attention_layernorm.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.index_k_norm.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.index_k_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.index_k_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.index_q_norm.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.index_q_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.index_q_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.k_norm.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.k_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.k_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.o_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.o_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.q_norm.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.q_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.q_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.v_proj.weight": "model-00054-of-00059.safetensors", + "language_model.model.layers.54.self_attn.v_proj.weight_scale": "model-00054-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.gate.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.108.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.108.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.108.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.108.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.108.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.108.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.109.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.109.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.109.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.109.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.109.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.109.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.11.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.11.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.11.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.11.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.11.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.11.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.110.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.110.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.110.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.110.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.110.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.110.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.111.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.111.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.111.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.111.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.111.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.111.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.112.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.112.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.112.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.112.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.112.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.112.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.113.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.113.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.113.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.113.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.113.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.113.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.114.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.114.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.114.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.114.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.114.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.114.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.115.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.115.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.115.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.115.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.115.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.115.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.116.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.116.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.116.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.116.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.116.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.116.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.117.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.117.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.117.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.117.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.117.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.117.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.118.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.118.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.118.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.118.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.118.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.118.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.119.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.119.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.119.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.119.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.119.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.119.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.12.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.12.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.12.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.12.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.12.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.12.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.120.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.120.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.120.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.120.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.120.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.120.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.121.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.121.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.121.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.121.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.121.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.121.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.122.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.122.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.122.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.122.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.122.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.122.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.123.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.123.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.123.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.123.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.123.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.123.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.124.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.124.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.124.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.124.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.124.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.124.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.125.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.125.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.125.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.125.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.125.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.125.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.126.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.126.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.126.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.126.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.126.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.126.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.127.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.127.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.127.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.127.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.127.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.127.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.13.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.13.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.13.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.13.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.13.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.13.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.14.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.14.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.14.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.14.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.14.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.14.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.15.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.15.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.15.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.15.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.15.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.15.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.16.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.16.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.16.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.16.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.16.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.16.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.17.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.17.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.17.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.17.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.17.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.17.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.18.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.18.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.18.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.18.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.18.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.18.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.19.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.19.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.19.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.19.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.19.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.19.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.2.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.2.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.2.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.20.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.20.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.20.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.20.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.20.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.20.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.21.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.21.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.21.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.21.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.21.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.21.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.22.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.22.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.22.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.22.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.22.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.22.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.23.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.23.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.23.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.23.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.23.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.23.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.24.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.24.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.24.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.24.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.24.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.24.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.25.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.25.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.25.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.25.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.25.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.25.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.26.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.26.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.26.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.26.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.26.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.26.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.27.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.27.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.27.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.27.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.27.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.27.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.28.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.28.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.28.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.28.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.28.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.28.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.29.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.29.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.29.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.29.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.29.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.29.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.3.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.3.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.3.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.3.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.3.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.3.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.30.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.30.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.30.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.30.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.30.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.30.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.31.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.31.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.31.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.31.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.31.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.31.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.32.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.32.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.32.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.32.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.32.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.32.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.33.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.33.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.33.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.33.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.33.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.33.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.34.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.34.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.34.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.34.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.34.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.34.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.35.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.35.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.35.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.35.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.35.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.35.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.36.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.36.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.36.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.36.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.36.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.36.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.37.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.37.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.37.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.37.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.37.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.37.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.38.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.38.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.38.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.38.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.38.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.38.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.39.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.39.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.39.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.39.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.39.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.39.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.4.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.4.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.4.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.4.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.4.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.4.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.40.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.40.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.40.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.40.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.40.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.40.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.41.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.41.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.41.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.41.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.41.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.41.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.42.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.42.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.42.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.42.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.42.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.42.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.43.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.43.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.43.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.43.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.43.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.43.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.44.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.44.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.44.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.44.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.44.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.44.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.45.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.45.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.45.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.45.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.45.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.45.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.46.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.46.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.46.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.46.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.46.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.46.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.47.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.47.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.47.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.47.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.47.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.47.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.48.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.48.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.48.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.48.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.48.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.48.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.49.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.49.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.49.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.49.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.49.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.49.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.5.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.5.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.5.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.5.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.5.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.5.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.50.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.50.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.50.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.50.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.50.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.50.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.51.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.51.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.51.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.51.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.51.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.51.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.52.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.52.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.52.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.52.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.52.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.52.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.53.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.53.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.53.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.53.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.53.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.53.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.54.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.54.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.54.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.54.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.54.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.54.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.55.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.55.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.55.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.55.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.55.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.55.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.56.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.56.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.56.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.56.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.56.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.56.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.57.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.57.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.57.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.57.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.57.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.57.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.58.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.58.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.58.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.58.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.58.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.58.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.59.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.59.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.59.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.59.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.59.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.59.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.6.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.6.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.6.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.6.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.6.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.6.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.60.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.60.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.60.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.60.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.60.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.60.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.61.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.61.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.61.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.61.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.61.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.61.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.62.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.62.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.62.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.62.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.62.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.62.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.63.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.63.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.63.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.63.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.63.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.63.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.64.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.64.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.64.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.64.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.64.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.64.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.65.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.65.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.65.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.65.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.65.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.65.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.66.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.66.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.66.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.66.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.66.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.66.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.67.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.67.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.67.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.67.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.67.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.67.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.68.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.68.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.68.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.68.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.68.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.68.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.69.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.69.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.69.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.69.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.69.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.69.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.7.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.7.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.7.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.7.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.7.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.7.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.70.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.70.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.70.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.70.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.70.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.70.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.71.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.71.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.71.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.71.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.71.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.71.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.72.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.72.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.72.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.72.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.72.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.72.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.73.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.73.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.73.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.73.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.73.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.73.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.74.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.74.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.74.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.74.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.74.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.74.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.75.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.75.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.75.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.75.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.75.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.75.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.76.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.76.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.76.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.76.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.76.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.76.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.77.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.77.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.77.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.77.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.77.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.77.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.78.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.78.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.78.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.78.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.78.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.78.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.79.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.79.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.79.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.79.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.79.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.79.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.8.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.8.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.8.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.8.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.8.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.8.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.80.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.80.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.80.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.80.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.80.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.80.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.81.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.81.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.81.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.81.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.81.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.81.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.82.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.82.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.82.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.82.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.82.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.82.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.83.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.83.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.83.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.83.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.83.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.83.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.84.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.84.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.84.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.84.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.84.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.84.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.85.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.85.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.85.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.85.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.85.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.85.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.86.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.86.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.86.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.86.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.86.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.86.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.87.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.87.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.87.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.87.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.87.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.87.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.88.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.88.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.88.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.88.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.88.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.88.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.89.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.89.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.89.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.89.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.89.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.89.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.9.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.9.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.9.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.9.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.9.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.9.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.90.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.90.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.90.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.90.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.90.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.90.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.91.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.91.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.91.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.91.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.91.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.91.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.92.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.92.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.92.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.92.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.92.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.92.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.93.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.93.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.93.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.93.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.93.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.93.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.94.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.94.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.94.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.94.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.94.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.94.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.95.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.95.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.95.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.95.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.95.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.95.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.96.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.96.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.96.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.96.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.96.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.96.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.97.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.97.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.97.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.97.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.97.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.97.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.98.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.98.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.98.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.98.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.98.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.98.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.99.w1.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.99.w1.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.99.w2.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.99.w2.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.99.w3.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.99.w3.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.shared_experts.down_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.shared_experts.gate_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.shared_experts.up_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.input_layernorm.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.post_attention_layernorm.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.index_k_norm.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.index_k_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.index_k_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.index_q_norm.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.index_q_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.index_q_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.k_norm.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.k_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.k_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.o_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.o_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.q_norm.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.q_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.q_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.v_proj.weight": "model-00053-of-00059.safetensors", + "language_model.model.layers.53.self_attn.v_proj.weight_scale": "model-00053-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.gate.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.108.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.108.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.108.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.108.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.108.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.108.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.109.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.109.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.109.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.109.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.109.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.109.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.11.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.11.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.11.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.11.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.11.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.11.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.110.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.110.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.110.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.110.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.110.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.110.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.111.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.111.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.111.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.111.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.111.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.111.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.112.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.112.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.112.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.112.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.112.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.112.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.113.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.113.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.113.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.113.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.113.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.113.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.114.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.114.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.114.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.114.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.114.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.114.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.115.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.115.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.115.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.115.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.115.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.115.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.116.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.116.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.116.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.116.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.116.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.116.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.117.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.117.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.117.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.117.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.117.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.117.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.118.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.118.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.118.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.118.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.118.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.118.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.119.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.119.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.119.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.119.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.119.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.119.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.12.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.12.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.12.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.12.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.12.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.12.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.120.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.120.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.120.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.120.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.120.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.120.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.121.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.121.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.121.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.121.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.121.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.121.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.122.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.122.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.122.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.122.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.122.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.122.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.123.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.123.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.123.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.123.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.123.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.123.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.124.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.124.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.124.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.124.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.124.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.124.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.125.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.125.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.125.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.125.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.125.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.125.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.126.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.126.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.126.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.126.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.126.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.126.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.127.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.127.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.127.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.127.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.127.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.127.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.13.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.13.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.13.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.13.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.13.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.13.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.14.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.14.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.14.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.14.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.14.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.14.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.15.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.15.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.15.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.15.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.15.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.15.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.16.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.16.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.16.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.16.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.16.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.16.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.17.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.17.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.17.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.17.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.17.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.17.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.18.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.18.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.18.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.18.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.18.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.18.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.19.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.19.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.19.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.19.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.19.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.19.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.2.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.2.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.2.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.20.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.20.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.20.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.20.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.20.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.20.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.21.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.21.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.21.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.21.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.21.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.21.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.22.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.22.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.22.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.22.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.22.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.22.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.23.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.23.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.23.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.23.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.23.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.23.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.24.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.24.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.24.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.24.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.24.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.24.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.25.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.25.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.25.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.25.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.25.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.25.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.26.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.26.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.26.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.26.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.26.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.26.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.27.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.27.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.27.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.27.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.27.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.27.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.28.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.28.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.28.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.28.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.28.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.28.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.29.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.29.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.29.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.29.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.29.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.29.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.3.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.3.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.3.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.30.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.30.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.30.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.30.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.30.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.30.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.31.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.31.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.31.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.31.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.31.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.31.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.32.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.32.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.32.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.32.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.32.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.32.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.33.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.33.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.33.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.33.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.33.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.33.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.34.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.34.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.34.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.34.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.34.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.34.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.35.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.35.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.35.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.35.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.35.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.35.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.36.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.36.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.36.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.36.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.36.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.36.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.37.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.37.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.37.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.37.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.37.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.37.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.38.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.38.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.38.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.38.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.38.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.38.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.39.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.39.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.39.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.39.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.39.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.39.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.4.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.4.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.4.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.4.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.4.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.4.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.40.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.40.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.40.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.40.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.40.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.40.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.41.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.41.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.41.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.41.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.41.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.41.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.42.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.42.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.42.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.42.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.42.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.42.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.43.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.43.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.43.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.43.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.43.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.43.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.44.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.44.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.44.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.44.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.44.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.44.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.45.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.45.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.45.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.45.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.45.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.45.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.46.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.46.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.46.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.46.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.46.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.46.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.47.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.47.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.47.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.47.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.47.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.47.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.48.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.48.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.48.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.48.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.48.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.48.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.49.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.49.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.49.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.49.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.49.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.49.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.5.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.5.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.5.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.5.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.50.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.50.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.50.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.50.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.50.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.50.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.51.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.51.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.51.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.51.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.51.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.51.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.52.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.52.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.52.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.52.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.52.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.52.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.53.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.53.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.53.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.53.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.53.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.53.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.54.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.54.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.54.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.54.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.54.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.54.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.55.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.55.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.55.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.55.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.55.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.55.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.56.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.56.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.56.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.56.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.56.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.56.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.57.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.57.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.57.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.57.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.57.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.57.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.58.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.58.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.58.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.58.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.58.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.58.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.59.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.59.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.59.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.59.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.59.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.59.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.6.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.6.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.6.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.60.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.60.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.60.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.60.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.60.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.60.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.61.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.61.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.61.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.61.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.61.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.61.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.62.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.62.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.62.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.62.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.62.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.62.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.63.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.63.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.63.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.63.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.63.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.63.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.64.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.64.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.64.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.64.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.64.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.64.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.65.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.65.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.65.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.65.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.65.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.65.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.66.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.66.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.66.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.66.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.66.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.66.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.67.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.67.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.67.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.67.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.67.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.67.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.68.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.68.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.68.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.68.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.68.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.68.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.69.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.69.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.69.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.69.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.69.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.69.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.7.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.7.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.7.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.7.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.70.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.70.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.70.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.70.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.70.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.70.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.71.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.71.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.71.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.71.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.71.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.71.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.72.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.72.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.72.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.72.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.72.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.72.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.73.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.73.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.73.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.73.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.73.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.73.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.74.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.74.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.74.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.74.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.74.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.74.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.75.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.75.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.75.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.75.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.75.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.75.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.76.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.76.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.76.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.76.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.76.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.76.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.77.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.77.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.77.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.77.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.77.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.77.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.78.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.78.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.78.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.78.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.78.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.78.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.79.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.79.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.79.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.79.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.79.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.79.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.8.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.8.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.8.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.8.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.8.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.8.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.80.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.80.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.80.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.80.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.80.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.80.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.81.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.81.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.81.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.81.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.81.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.81.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.82.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.82.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.82.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.82.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.82.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.82.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.83.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.83.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.83.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.83.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.83.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.83.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.84.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.84.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.84.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.84.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.84.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.84.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.85.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.85.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.85.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.85.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.85.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.85.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.86.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.86.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.86.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.86.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.86.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.86.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.87.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.87.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.87.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.87.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.87.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.87.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.88.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.88.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.88.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.88.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.88.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.88.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.89.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.89.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.89.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.89.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.89.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.89.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.9.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.9.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.9.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.9.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.9.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.9.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.90.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.90.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.90.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.90.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.90.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.90.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.91.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.91.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.91.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.91.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.91.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.91.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.92.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.92.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.92.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.92.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.92.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.92.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.93.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.93.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.93.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.93.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.93.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.93.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.94.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.94.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.94.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.94.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.94.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.94.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.95.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.95.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.95.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.95.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.95.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.95.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.96.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.96.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.96.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.96.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.96.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.96.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.97.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.97.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.97.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.97.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.97.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.97.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.98.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.98.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.98.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.98.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.98.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.98.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.99.w1.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.99.w1.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.99.w2.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.99.w2.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.99.w3.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.99.w3.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.shared_experts.down_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.shared_experts.gate_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.shared_experts.up_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.input_layernorm.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.post_attention_layernorm.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.index_k_norm.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.index_k_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.index_k_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.index_q_norm.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.index_q_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.index_q_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.k_norm.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.k_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.k_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.o_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.o_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.q_norm.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.q_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.q_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.v_proj.weight": "model-00042-of-00059.safetensors", + "language_model.model.layers.42.self_attn.v_proj.weight_scale": "model-00042-of-00059.safetensors", + "language_model.lm_head.weight": "model-00001-of-00059.safetensors", + "language_model.model.embed_tokens.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00059.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00059.safetensors", + "language_model.model.norm.weight": "model-00001-of-00059.safetensors", "language_model.model.layers.59.block_sparse_moe.e_score_correction_bias": "model-00059-of-00059.safetensors", "language_model.model.layers.59.block_sparse_moe.gate.weight": "model-00059-of-00059.safetensors", "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00059-of-00059.safetensors", @@ -45200,8 +3844,10 @@ "language_model.model.layers.59.post_attention_layernorm.weight": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.index_k_norm.weight": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.index_k_proj.weight": "model-00059-of-00059.safetensors", + "language_model.model.layers.59.self_attn.index_k_proj.weight_scale": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.index_q_norm.weight": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.index_q_proj.weight": "model-00059-of-00059.safetensors", + "language_model.model.layers.59.self_attn.index_q_proj.weight_scale": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.k_norm.weight": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.k_proj.weight": "model-00059-of-00059.safetensors", "language_model.model.layers.59.self_attn.k_proj.weight_scale": "model-00059-of-00059.safetensors", @@ -45726,6 +4372,41465 @@ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00059-of-00059.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00059-of-00059.safetensors", "vision_tower.vision_model.pre_layrnorm.bias": "model-00059-of-00059.safetensors", - "vision_tower.vision_model.pre_layrnorm.weight": "model-00059-of-00059.safetensors" + "vision_tower.vision_model.pre_layrnorm.weight": "model-00059-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.gate.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.108.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.108.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.108.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.108.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.108.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.108.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.109.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.109.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.109.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.109.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.109.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.109.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.11.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.11.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.11.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.11.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.11.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.11.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.110.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.110.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.110.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.110.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.110.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.110.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.111.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.111.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.111.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.111.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.111.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.111.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.112.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.112.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.112.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.112.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.112.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.112.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.113.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.113.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.113.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.113.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.113.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.113.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.114.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.114.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.114.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.114.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.114.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.114.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.115.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.115.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.115.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.115.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.115.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.115.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.116.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.116.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.116.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.116.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.116.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.116.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.117.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.117.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.117.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.117.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.117.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.117.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.118.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.118.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.118.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.118.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.118.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.118.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.119.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.119.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.119.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.119.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.119.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.119.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.12.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.12.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.12.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.12.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.12.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.12.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.120.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.120.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.120.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.120.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.120.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.120.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.121.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.121.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.121.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.121.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.121.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.121.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.122.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.122.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.122.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.122.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.122.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.122.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.123.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.123.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.123.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.123.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.123.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.123.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.124.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.124.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.124.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.124.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.124.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.124.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.125.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.125.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.125.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.125.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.125.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.125.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.126.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.126.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.126.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.126.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.126.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.126.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.127.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.127.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.127.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.127.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.127.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.127.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.13.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.13.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.13.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.13.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.13.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.13.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.14.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.14.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.14.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.14.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.14.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.14.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.15.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.15.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.15.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.15.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.15.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.15.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.16.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.16.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.16.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.16.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.16.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.16.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.17.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.17.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.17.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.17.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.17.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.17.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.18.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.18.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.18.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.18.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.18.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.18.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.19.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.19.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.19.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.19.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.19.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.19.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.2.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.2.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.2.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.2.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.2.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.2.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.20.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.20.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.20.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.20.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.20.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.20.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.21.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.21.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.21.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.21.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.21.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.21.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.22.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.22.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.22.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.22.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.22.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.22.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.23.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.23.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.23.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.23.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.23.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.23.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.24.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.24.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.24.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.24.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.24.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.24.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.25.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.25.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.25.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.25.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.25.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.25.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.26.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.26.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.26.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.26.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.26.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.26.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.27.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.27.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.27.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.27.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.27.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.27.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.28.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.28.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.28.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.28.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.28.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.28.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.29.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.29.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.29.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.29.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.29.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.29.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.3.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.3.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.3.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.3.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.3.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.3.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.30.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.30.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.30.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.30.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.30.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.30.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.31.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.31.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.31.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.31.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.31.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.31.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.32.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.32.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.32.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.32.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.32.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.32.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.33.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.33.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.33.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.33.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.33.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.33.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.34.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.34.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.34.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.34.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.34.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.34.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.35.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.35.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.35.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.35.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.35.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.35.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.36.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.36.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.36.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.36.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.36.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.36.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.37.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.37.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.37.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.37.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.37.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.37.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.38.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.38.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.38.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.38.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.38.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.38.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.39.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.39.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.39.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.39.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.39.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.39.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.4.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.4.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.4.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.4.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.4.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.4.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.40.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.40.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.40.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.40.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.40.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.40.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.41.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.41.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.41.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.41.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.41.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.41.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.42.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.42.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.42.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.42.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.42.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.42.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.43.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.43.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.43.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.43.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.43.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.43.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.44.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.44.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.44.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.44.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.44.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.44.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.45.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.45.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.45.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.45.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.45.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.45.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.46.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.46.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.46.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.46.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.46.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.46.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.47.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.47.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.47.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.47.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.47.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.47.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.48.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.48.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.48.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.48.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.48.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.48.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.49.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.49.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.49.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.49.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.49.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.49.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.5.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.5.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.5.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.5.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.5.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.5.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.50.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.50.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.50.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.50.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.50.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.50.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.51.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.51.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.51.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.51.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.51.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.51.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.52.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.52.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.52.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.52.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.52.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.52.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.53.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.53.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.53.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.53.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.53.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.53.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.54.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.54.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.54.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.54.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.54.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.54.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.55.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.55.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.55.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.55.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.55.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.55.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.56.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.56.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.56.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.56.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.56.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.56.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.57.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.57.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.57.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.57.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.57.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.57.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.58.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.58.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.58.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.58.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.58.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.58.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.59.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.59.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.59.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.59.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.59.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.59.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.6.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.6.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.6.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.6.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.6.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.6.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.60.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.60.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.60.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.60.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.60.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.60.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.61.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.61.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.61.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.61.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.61.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.61.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.62.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.62.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.62.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.62.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.62.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.62.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.63.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.63.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.63.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.63.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.63.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.63.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.64.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.64.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.64.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.64.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.64.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.64.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.65.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.65.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.65.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.65.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.65.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.65.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.66.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.66.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.66.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.66.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.66.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.66.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.67.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.67.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.67.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.67.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.67.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.67.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.68.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.68.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.68.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.68.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.68.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.68.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.69.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.69.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.69.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.69.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.69.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.69.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.7.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.7.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.7.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.7.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.7.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.7.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.70.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.70.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.70.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.70.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.70.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.70.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.71.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.71.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.71.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.71.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.71.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.71.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.72.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.72.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.72.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.72.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.72.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.72.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.73.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.73.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.73.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.73.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.73.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.73.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.74.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.74.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.74.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.74.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.74.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.74.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.75.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.75.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.75.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.75.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.75.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.75.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.76.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.76.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.76.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.76.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.76.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.76.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.77.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.77.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.77.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.77.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.77.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.77.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.78.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.78.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.78.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.78.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.78.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.78.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.79.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.79.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.79.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.79.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.79.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.79.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.8.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.8.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.8.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.8.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.8.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.8.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.80.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.80.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.80.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.80.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.80.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.80.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.81.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.81.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.81.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.81.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.81.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.81.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.82.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.82.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.82.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.82.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.82.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.82.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.83.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.83.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.83.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.83.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.83.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.83.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.84.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.84.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.84.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.84.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.84.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.84.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.85.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.85.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.85.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.85.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.85.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.85.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.86.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.86.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.86.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.86.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.86.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.86.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.87.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.87.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.87.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.87.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.87.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.87.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.88.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.88.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.88.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.88.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.88.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.88.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.89.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.89.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.89.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.89.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.89.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.89.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.9.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.9.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.9.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.9.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.9.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.9.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.90.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.90.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.90.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.90.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.90.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.90.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.91.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.91.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.91.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.91.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.91.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.91.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.92.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.92.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.92.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.92.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.92.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.92.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.93.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.93.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.93.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.93.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.93.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.93.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.94.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.94.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.94.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.94.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.94.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.94.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.95.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.95.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.95.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.95.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.95.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.95.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.96.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.96.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.96.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.96.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.96.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.96.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.97.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.97.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.97.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.97.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.97.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.97.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.98.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.98.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.98.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.98.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.98.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.98.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.99.w1.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.99.w1.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.99.w2.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.99.w2.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.99.w3.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.99.w3.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.shared_experts.down_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.shared_experts.gate_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.shared_experts.up_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.input_layernorm.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.post_attention_layernorm.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.index_k_norm.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.index_k_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.index_k_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.index_q_norm.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.index_q_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.index_q_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.k_norm.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.k_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.k_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.o_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.o_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.q_norm.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.q_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.q_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.v_proj.weight": "model-00056-of-00059.safetensors", + "language_model.model.layers.56.self_attn.v_proj.weight_scale": "model-00056-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.e_score_correction_bias": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.gate.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.e_score_correction_bias": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.0.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.0.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.0.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.1.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.1.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.1.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.10.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.10.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.10.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.100.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.100.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.100.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.101.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.101.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.101.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.102.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.102.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.102.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.103.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.103.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.103.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.104.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.104.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.104.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.105.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.105.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.105.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.106.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.106.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.106.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.107.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.107.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.107.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.108.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.108.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.108.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.108.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.108.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.108.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.109.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.109.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.109.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.109.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.109.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.109.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.11.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.11.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.11.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.110.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.110.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.110.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.110.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.110.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.110.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.111.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.111.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.111.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.111.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.111.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.111.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.112.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.112.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.112.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.112.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.112.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.112.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.113.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.113.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.113.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.113.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.113.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.113.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.114.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.114.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.114.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.114.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.114.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.114.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.115.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.115.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.115.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.115.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.115.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.115.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.116.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.116.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.116.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.116.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.116.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.116.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.117.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.117.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.117.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.117.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.117.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.117.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.118.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.118.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.118.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.118.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.118.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.118.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.119.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.119.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.119.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.119.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.119.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.119.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.12.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.12.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.12.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.120.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.120.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.120.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.120.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.120.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.120.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.121.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.121.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.121.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.121.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.121.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.121.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.122.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.122.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.122.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.122.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.122.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.122.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.123.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.123.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.123.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.123.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.123.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.123.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.124.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.124.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.124.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.124.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.124.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.124.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.125.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.125.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.125.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.125.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.125.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.125.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.126.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.126.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.126.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.126.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.126.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.126.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.127.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.127.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.127.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.127.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.127.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.127.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.13.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.13.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.13.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.14.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.14.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.14.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.15.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.15.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.15.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.16.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.16.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.16.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.17.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.17.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.17.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.18.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.18.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.18.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.19.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.19.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.19.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.2.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.2.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.2.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.20.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.20.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.20.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.21.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.21.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.21.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.22.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.22.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.22.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.23.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.23.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.23.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.24.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.24.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.24.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.25.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.25.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.25.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.26.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.26.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.26.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.27.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.27.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.27.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.28.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.28.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.28.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.29.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.29.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.29.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.3.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.3.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.3.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.30.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.30.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.30.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.31.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.31.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.31.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.32.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.32.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.32.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.32.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.32.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.32.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.33.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.33.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.33.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.33.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.33.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.33.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.34.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.34.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.34.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.34.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.34.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.34.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.35.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.35.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.35.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.35.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.35.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.35.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.36.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.36.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.36.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.36.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.36.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.36.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.37.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.37.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.37.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.37.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.37.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.37.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.38.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.38.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.38.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.38.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.38.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.38.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.39.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.39.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.39.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.39.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.39.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.39.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.4.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.4.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.4.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.40.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.40.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.40.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.40.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.40.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.40.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.41.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.41.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.41.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.41.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.41.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.41.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.42.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.42.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.42.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.42.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.42.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.42.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.43.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.43.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.43.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.43.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.43.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.43.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.44.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.44.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.44.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.44.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.44.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.44.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.45.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.45.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.45.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.45.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.45.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.45.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.46.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.46.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.46.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.46.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.46.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.46.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.47.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.47.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.47.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.47.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.47.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.47.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.48.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.48.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.48.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.48.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.48.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.48.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.49.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.49.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.49.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.49.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.49.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.49.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.5.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.5.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.5.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.50.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.50.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.50.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.50.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.50.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.50.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.51.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.51.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.51.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.51.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.51.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.51.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.52.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.52.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.52.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.52.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.52.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.52.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.53.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.53.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.53.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.53.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.53.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.53.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.54.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.54.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.54.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.54.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.54.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.54.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.55.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.55.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.55.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.55.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.55.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.55.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.56.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.56.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.56.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.56.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.56.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.56.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.57.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.57.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.57.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.57.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.57.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.57.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.58.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.58.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.58.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.58.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.58.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.58.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.59.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.59.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.59.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.59.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.59.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.59.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.6.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.6.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.6.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.60.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.60.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.60.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.60.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.60.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.60.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.61.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.61.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.61.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.61.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.61.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.61.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.62.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.62.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.62.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.62.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.62.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.62.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.63.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.63.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.63.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.63.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.63.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.63.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.64.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.64.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.64.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.64.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.64.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.64.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.65.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.65.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.65.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.65.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.65.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.65.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.66.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.66.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.66.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.66.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.66.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.66.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.67.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.67.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.67.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.67.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.67.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.67.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.68.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.68.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.68.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.68.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.68.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.68.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.69.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.69.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.69.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.69.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.69.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.69.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.7.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.7.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.7.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.70.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.70.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.70.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.70.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.70.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.70.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.71.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.71.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.71.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.71.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.71.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.71.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.72.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.72.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.72.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.72.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.72.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.72.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.73.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.73.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.73.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.73.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.73.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.73.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.74.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.74.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.74.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.74.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.74.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.74.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.75.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.75.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.75.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.75.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.75.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.75.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.76.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.76.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.76.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.76.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.76.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.76.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.77.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.77.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.77.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.77.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.77.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.77.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.78.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.78.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.78.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.78.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.78.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.78.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.79.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.79.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.79.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.79.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.79.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.79.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.8.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.8.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.8.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.80.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.80.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.80.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.80.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.80.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.80.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.81.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.81.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.81.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.81.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.81.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.81.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.82.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.82.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.82.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.82.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.82.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.83.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.83.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.83.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.84.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.84.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.84.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.85.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.85.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.85.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.86.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.86.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.86.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.87.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.87.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.87.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.88.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.88.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.88.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.88.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.88.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.89.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.89.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.89.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.89.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.89.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.89.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.9.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.9.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.9.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.90.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.90.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.90.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.90.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.90.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.90.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.91.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.91.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.91.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.91.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.91.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.91.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.92.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.92.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.92.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.92.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.92.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.92.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.93.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.93.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.93.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.93.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.93.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.93.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.94.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.94.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.94.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.94.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.94.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.94.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.95.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.95.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.95.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.95.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.95.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.95.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.96.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.96.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.96.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.96.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.96.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.96.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.97.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.97.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.97.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.97.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.97.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.97.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.98.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.98.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.98.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.98.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.98.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.98.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.99.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.99.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.99.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.99.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.99.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.experts.99.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.shared_experts.down_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.shared_experts.gate_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.shared_experts.up_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.index_k_norm.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.index_k_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.index_k_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.index_q_norm.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.index_q_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.index_q_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.k_norm.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.q_norm.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.0.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.0.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.0.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.1.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.1.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.1.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.10.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.10.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.10.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.100.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.100.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.100.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.101.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.101.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.101.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.102.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.102.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.102.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.103.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.103.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.103.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.104.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.104.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.104.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.105.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.105.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.105.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.106.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.106.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.106.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.107.w1.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.107.w2.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.107.w3.weight_scale": "model-00015-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.e_score_correction_bias": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.gate.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.0.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.0.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.0.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.1.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.1.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.1.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.10.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.10.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.10.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.10.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.10.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.10.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.100.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.100.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.100.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.100.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.100.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.100.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.101.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.101.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.101.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.101.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.101.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.101.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.102.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.102.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.102.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.102.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.102.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.102.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.103.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.103.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.103.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.103.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.103.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.103.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.104.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.104.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.104.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.104.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.104.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.104.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.105.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.105.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.105.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.105.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.105.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.105.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.106.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.106.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.106.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.106.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.106.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.106.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.107.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.107.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.107.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.107.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.107.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.107.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.108.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.108.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.108.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.108.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.108.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.108.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.109.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.109.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.109.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.109.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.109.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.109.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.11.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.11.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.11.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.11.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.11.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.11.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.110.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.110.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.110.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.110.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.110.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.110.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.111.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.111.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.111.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.111.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.111.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.111.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.112.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.112.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.112.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.112.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.112.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.112.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.113.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.113.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.113.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.113.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.113.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.113.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.114.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.114.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.114.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.114.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.114.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.114.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.115.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.115.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.115.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.115.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.115.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.115.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.116.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.116.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.116.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.116.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.116.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.116.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.117.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.117.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.117.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.117.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.117.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.117.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.118.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.118.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.118.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.118.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.118.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.118.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.119.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.119.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.119.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.119.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.119.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.119.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.12.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.12.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.12.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.12.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.12.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.12.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.120.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.120.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.120.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.120.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.120.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.120.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.121.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.121.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.121.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.121.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.121.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.121.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.122.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.122.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.122.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.122.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.122.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.122.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.123.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.123.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.123.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.123.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.123.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.123.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.124.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.124.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.124.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.124.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.124.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.124.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.125.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.125.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.125.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.125.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.125.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.125.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.126.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.126.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.126.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.126.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.126.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.126.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.127.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.127.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.127.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.127.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.127.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.127.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.13.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.13.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.13.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.13.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.13.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.13.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.14.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.14.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.14.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.14.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.14.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.14.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.15.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.15.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.15.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.15.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.15.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.15.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.16.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.16.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.16.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.16.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.16.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.16.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.17.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.17.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.17.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.17.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.17.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.17.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.18.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.18.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.18.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.18.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.18.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.18.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.19.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.19.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.19.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.19.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.19.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.19.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.2.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.2.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.2.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.20.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.20.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.20.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.20.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.20.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.20.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.21.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.21.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.21.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.21.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.21.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.21.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.22.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.22.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.22.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.22.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.22.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.22.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.23.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.23.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.23.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.23.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.23.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.23.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.24.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.24.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.24.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.24.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.24.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.24.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.25.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.25.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.25.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.25.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.25.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.25.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.26.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.26.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.26.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.26.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.26.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.26.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.27.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.27.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.27.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.27.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.27.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.27.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.28.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.28.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.28.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.28.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.28.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.28.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.29.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.29.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.29.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.29.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.29.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.29.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.3.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.3.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.3.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.30.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.30.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.30.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.30.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.30.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.30.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.31.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.31.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.31.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.31.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.31.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.31.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.32.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.32.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.32.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.32.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.32.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.32.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.33.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.33.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.33.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.33.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.33.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.33.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.34.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.34.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.34.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.34.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.34.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.34.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.35.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.35.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.35.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.35.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.35.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.35.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.36.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.36.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.36.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.36.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.36.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.36.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.37.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.37.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.37.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.37.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.37.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.37.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.38.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.38.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.38.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.38.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.38.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.38.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.39.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.39.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.39.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.39.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.39.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.39.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.4.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.4.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.4.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.40.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.40.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.40.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.40.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.40.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.40.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.41.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.41.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.41.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.41.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.41.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.41.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.42.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.42.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.42.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.42.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.42.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.42.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.43.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.43.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.43.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.43.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.43.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.43.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.44.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.44.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.44.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.44.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.44.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.44.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.45.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.45.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.45.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.45.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.45.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.45.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.46.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.46.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.46.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.46.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.46.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.46.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.47.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.47.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.47.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.47.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.47.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.47.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.48.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.48.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.48.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.48.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.48.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.48.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.49.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.49.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.49.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.49.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.49.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.49.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.5.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.5.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.5.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.50.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.50.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.50.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.50.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.50.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.50.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.51.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.51.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.51.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.51.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.51.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.51.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.52.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.52.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.52.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.52.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.52.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.52.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.53.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.53.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.53.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.53.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.53.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.53.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.54.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.54.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.54.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.54.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.54.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.54.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.55.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.55.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.55.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.55.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.55.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.55.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.56.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.56.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.56.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.56.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.56.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.56.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.57.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.57.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.57.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.57.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.57.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.57.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.58.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.58.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.58.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.58.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.58.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.58.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.59.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.59.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.59.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.59.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.59.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.59.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.6.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.6.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.6.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.60.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.60.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.60.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.60.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.60.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.60.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.61.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.61.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.61.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.61.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.61.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.61.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.62.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.62.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.62.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.62.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.62.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.62.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.63.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.63.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.63.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.63.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.63.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.63.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.64.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.64.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.64.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.64.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.64.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.64.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.65.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.65.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.65.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.65.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.65.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.65.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.66.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.66.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.66.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.66.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.66.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.66.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.67.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.67.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.67.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.67.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.67.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.67.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.68.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.68.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.68.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.68.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.68.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.68.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.69.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.69.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.69.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.69.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.69.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.69.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.7.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.7.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.7.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.70.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.70.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.70.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.70.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.70.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.70.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.71.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.71.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.71.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.71.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.71.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.71.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.72.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.72.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.72.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.72.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.72.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.72.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.73.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.73.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.73.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.73.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.73.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.73.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.74.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.74.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.74.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.74.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.74.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.74.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.75.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.75.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.75.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.75.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.75.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.75.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.76.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.76.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.76.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.76.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.76.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.76.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.77.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.77.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.77.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.77.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.77.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.77.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.78.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.78.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.78.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.78.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.78.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.78.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.79.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.79.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.79.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.79.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.79.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.79.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.8.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.8.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.8.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.8.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.8.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.8.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.80.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.80.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.80.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.80.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.80.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.80.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.81.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.81.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.81.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.81.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.81.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.81.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.82.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.82.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.82.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.82.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.82.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.82.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.83.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.83.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.83.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.83.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.83.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.83.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.84.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.84.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.84.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.84.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.84.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.84.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.85.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.85.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.85.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.85.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.85.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.85.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.86.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.86.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.86.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.86.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.86.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.86.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.87.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.87.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.87.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.87.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.87.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.87.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.88.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.88.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.88.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.88.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.88.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.88.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.89.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.89.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.89.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.89.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.89.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.89.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.9.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.9.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.9.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.9.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.9.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.9.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.90.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.90.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.90.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.90.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.90.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.90.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.91.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.91.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.91.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.91.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.91.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.91.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.92.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.92.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.92.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.92.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.92.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.92.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.93.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.93.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.93.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.93.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.93.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.93.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.94.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.94.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.94.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.94.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.94.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.94.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.95.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.95.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.95.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.95.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.95.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.95.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.96.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.96.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.96.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.96.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.96.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.96.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.97.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.97.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.97.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.97.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.97.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.97.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.98.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.98.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.98.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.98.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.98.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.98.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.99.w1.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.99.w1.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.99.w2.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.99.w2.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.99.w3.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.experts.99.w3.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.shared_experts.down_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.shared_experts.gate_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.shared_experts.up_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.input_layernorm.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.post_attention_layernorm.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.index_k_norm.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.index_k_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.index_k_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.index_q_norm.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.index_q_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.index_q_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.k_norm.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.q_norm.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight": "model-00035-of-00059.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight_scale": "model-00035-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.gate.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.108.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.108.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.108.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.108.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.108.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.108.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.109.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.109.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.109.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.109.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.109.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.109.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.11.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.11.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.11.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.11.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.11.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.11.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.110.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.110.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.110.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.110.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.110.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.110.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.111.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.111.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.111.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.111.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.111.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.111.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.112.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.112.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.112.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.112.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.112.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.112.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.113.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.113.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.113.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.113.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.113.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.113.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.114.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.114.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.114.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.114.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.114.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.114.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.115.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.115.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.115.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.115.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.115.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.115.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.116.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.116.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.116.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.116.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.116.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.116.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.117.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.117.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.117.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.117.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.117.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.117.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.118.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.118.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.118.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.118.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.118.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.118.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.119.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.119.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.119.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.119.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.119.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.119.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.12.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.12.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.12.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.12.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.12.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.12.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.120.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.120.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.120.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.120.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.120.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.120.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.121.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.121.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.121.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.121.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.121.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.121.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.122.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.122.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.122.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.122.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.122.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.122.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.123.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.123.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.123.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.123.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.123.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.123.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.124.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.124.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.124.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.124.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.124.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.124.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.125.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.125.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.125.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.125.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.125.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.125.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.126.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.126.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.126.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.126.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.126.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.126.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.127.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.127.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.127.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.127.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.127.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.127.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.13.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.13.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.13.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.13.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.13.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.13.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.14.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.14.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.14.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.14.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.14.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.14.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.15.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.15.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.15.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.15.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.15.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.15.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.16.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.16.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.16.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.16.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.16.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.16.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.17.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.17.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.17.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.17.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.17.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.17.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.18.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.18.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.18.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.18.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.18.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.18.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.19.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.19.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.19.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.19.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.19.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.19.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.2.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.2.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.2.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.20.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.20.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.20.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.20.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.20.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.20.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.21.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.21.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.21.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.21.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.21.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.21.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.22.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.22.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.22.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.22.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.22.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.22.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.23.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.23.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.23.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.23.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.23.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.23.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.24.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.24.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.24.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.24.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.24.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.24.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.25.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.25.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.25.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.25.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.25.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.25.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.26.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.26.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.26.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.26.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.26.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.26.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.27.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.27.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.27.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.27.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.27.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.27.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.28.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.28.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.28.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.28.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.28.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.28.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.29.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.29.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.29.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.29.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.29.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.29.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.3.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.3.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.3.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.30.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.30.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.30.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.30.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.30.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.30.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.31.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.31.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.31.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.31.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.31.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.31.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.32.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.32.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.32.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.32.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.32.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.32.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.33.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.33.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.33.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.33.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.33.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.33.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.34.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.34.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.34.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.34.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.34.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.34.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.35.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.35.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.35.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.35.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.35.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.35.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.36.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.36.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.36.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.36.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.36.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.36.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.37.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.37.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.37.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.37.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.37.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.37.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.38.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.38.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.38.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.38.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.38.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.38.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.39.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.39.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.39.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.39.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.39.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.39.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.4.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.4.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.4.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.40.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.40.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.40.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.40.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.40.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.40.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.41.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.41.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.41.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.41.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.41.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.41.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.42.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.42.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.42.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.42.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.42.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.42.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.43.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.43.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.43.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.43.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.43.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.43.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.44.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.44.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.44.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.44.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.44.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.44.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.45.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.45.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.45.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.45.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.45.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.45.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.46.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.46.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.46.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.46.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.46.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.46.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.47.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.47.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.47.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.47.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.47.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.47.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.48.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.48.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.48.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.48.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.48.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.48.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.49.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.49.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.49.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.49.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.49.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.49.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.5.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.5.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.5.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.50.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.50.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.50.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.50.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.50.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.50.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.51.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.51.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.51.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.51.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.51.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.51.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.52.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.52.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.52.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.52.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.52.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.52.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.53.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.53.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.53.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.53.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.53.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.53.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.54.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.54.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.54.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.54.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.54.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.54.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.55.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.55.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.55.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.55.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.55.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.55.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.56.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.56.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.56.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.56.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.56.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.56.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.57.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.57.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.57.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.57.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.57.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.57.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.58.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.58.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.58.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.58.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.58.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.58.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.59.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.59.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.59.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.59.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.59.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.59.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.6.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.6.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.6.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.60.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.60.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.60.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.60.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.60.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.60.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.61.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.61.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.61.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.61.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.61.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.61.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.62.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.62.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.62.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.62.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.62.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.62.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.63.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.63.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.63.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.63.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.63.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.63.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.64.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.64.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.64.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.64.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.64.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.64.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.65.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.65.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.65.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.65.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.65.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.65.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.66.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.66.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.66.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.66.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.66.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.66.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.67.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.67.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.67.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.67.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.67.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.67.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.68.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.68.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.68.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.68.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.68.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.68.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.69.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.69.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.69.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.69.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.69.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.69.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.7.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.7.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.7.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.7.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.7.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.70.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.70.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.70.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.70.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.70.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.70.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.71.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.71.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.71.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.71.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.71.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.71.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.72.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.72.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.72.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.72.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.72.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.72.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.73.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.73.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.73.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.73.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.73.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.73.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.74.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.74.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.74.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.74.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.74.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.74.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.75.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.75.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.75.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.75.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.75.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.75.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.76.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.76.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.76.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.76.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.76.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.76.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.77.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.77.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.77.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.77.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.77.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.77.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.78.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.78.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.78.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.78.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.78.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.78.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.79.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.79.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.79.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.79.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.79.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.79.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.8.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.8.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.8.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.8.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.8.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.8.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.80.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.80.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.80.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.80.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.80.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.80.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.81.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.81.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.81.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.81.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.81.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.81.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.82.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.82.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.82.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.82.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.82.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.82.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.83.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.83.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.83.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.83.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.83.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.83.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.84.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.84.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.84.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.84.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.84.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.84.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.85.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.85.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.85.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.85.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.85.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.85.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.86.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.86.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.86.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.86.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.86.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.86.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.87.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.87.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.87.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.87.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.87.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.87.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.88.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.88.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.88.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.88.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.88.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.88.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.89.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.89.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.89.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.89.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.89.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.89.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.9.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.9.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.9.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.9.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.9.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.9.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.90.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.90.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.90.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.90.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.90.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.90.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.91.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.91.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.91.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.91.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.91.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.91.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.92.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.92.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.92.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.92.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.92.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.92.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.93.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.93.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.93.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.93.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.93.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.93.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.94.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.94.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.94.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.94.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.94.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.94.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.95.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.95.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.95.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.95.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.95.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.95.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.96.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.96.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.96.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.96.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.96.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.96.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.97.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.97.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.97.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.97.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.97.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.97.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.98.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.98.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.98.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.98.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.98.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.98.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.99.w1.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.99.w1.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.99.w2.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.99.w2.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.99.w3.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.99.w3.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.shared_experts.down_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.shared_experts.gate_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.shared_experts.up_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.input_layernorm.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.post_attention_layernorm.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.index_k_norm.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.index_k_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.index_k_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.index_q_norm.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.index_q_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.index_q_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.k_norm.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.k_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.k_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.o_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.o_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.q_norm.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.q_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.q_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.v_proj.weight": "model-00041-of-00059.safetensors", + "language_model.model.layers.41.self_attn.v_proj.weight_scale": "model-00041-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.e_score_correction_bias": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.gate.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.0.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.0.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.0.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.1.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.1.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.1.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.10.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.10.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.10.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.10.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.10.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.10.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.100.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.100.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.100.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.100.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.100.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.100.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.101.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.101.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.101.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.101.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.101.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.101.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.102.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.102.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.102.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.102.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.102.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.102.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.103.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.103.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.103.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.103.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.103.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.103.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.104.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.104.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.104.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.104.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.104.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.104.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.105.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.105.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.105.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.105.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.105.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.105.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.106.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.106.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.106.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.106.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.106.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.106.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.107.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.107.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.107.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.107.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.107.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.107.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.108.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.108.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.108.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.108.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.108.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.108.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.109.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.109.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.109.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.109.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.109.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.109.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.11.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.11.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.11.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.11.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.11.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.11.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.110.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.110.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.110.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.110.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.110.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.110.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.111.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.111.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.111.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.111.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.111.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.111.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.112.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.112.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.112.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.112.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.112.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.112.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.113.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.113.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.113.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.113.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.113.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.113.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.114.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.114.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.114.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.114.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.114.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.114.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.115.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.115.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.115.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.115.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.115.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.115.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.116.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.116.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.116.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.116.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.116.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.116.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.117.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.117.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.117.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.117.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.117.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.117.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.118.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.118.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.118.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.118.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.118.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.118.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.119.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.119.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.119.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.119.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.119.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.119.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.12.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.12.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.12.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.12.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.12.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.12.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.120.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.120.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.120.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.120.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.120.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.120.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.121.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.121.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.121.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.121.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.121.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.121.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.122.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.122.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.122.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.122.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.122.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.122.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.123.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.123.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.123.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.123.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.123.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.123.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.124.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.124.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.124.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.124.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.124.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.124.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.125.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.125.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.125.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.125.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.125.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.125.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.126.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.126.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.126.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.126.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.126.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.126.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.127.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.127.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.127.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.127.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.127.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.127.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.13.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.13.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.13.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.13.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.13.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.13.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.14.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.14.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.14.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.14.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.14.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.14.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.15.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.15.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.15.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.15.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.15.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.15.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.16.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.16.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.16.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.16.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.16.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.16.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.17.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.17.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.17.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.17.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.17.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.17.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.18.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.18.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.18.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.18.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.18.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.18.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.19.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.19.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.19.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.19.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.19.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.19.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.2.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.2.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.2.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.20.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.20.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.20.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.20.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.20.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.20.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.21.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.21.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.21.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.21.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.21.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.21.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.22.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.22.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.22.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.22.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.22.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.22.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.23.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.23.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.23.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.23.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.23.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.23.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.24.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.24.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.24.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.24.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.24.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.24.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.25.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.25.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.25.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.25.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.25.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.25.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.26.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.26.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.26.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.26.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.26.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.26.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.27.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.27.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.27.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.27.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.27.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.27.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.28.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.28.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.28.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.28.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.28.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.28.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.29.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.29.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.29.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.29.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.29.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.29.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.3.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.3.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.3.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.30.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.30.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.30.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.30.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.30.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.30.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.31.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.31.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.31.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.31.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.31.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.31.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.32.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.32.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.32.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.32.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.32.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.32.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.33.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.33.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.33.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.33.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.33.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.33.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.34.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.34.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.34.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.34.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.34.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.34.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.35.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.35.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.35.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.35.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.35.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.35.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.36.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.36.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.36.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.36.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.36.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.36.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.37.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.37.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.37.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.37.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.37.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.37.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.38.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.38.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.38.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.38.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.38.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.38.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.39.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.39.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.39.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.39.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.39.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.39.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.4.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.4.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.4.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.40.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.40.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.40.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.40.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.40.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.40.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.41.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.41.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.41.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.41.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.41.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.41.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.42.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.42.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.42.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.42.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.42.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.42.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.43.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.43.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.43.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.43.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.43.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.43.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.44.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.44.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.44.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.44.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.44.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.44.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.45.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.45.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.45.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.45.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.45.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.45.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.46.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.46.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.46.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.46.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.46.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.46.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.47.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.47.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.47.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.47.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.47.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.47.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.48.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.48.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.48.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.48.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.48.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.48.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.49.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.49.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.49.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.49.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.49.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.49.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.5.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.5.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.5.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.50.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.50.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.50.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.50.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.50.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.50.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.51.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.51.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.51.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.51.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.51.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.51.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.52.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.52.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.52.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.52.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.52.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.52.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.53.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.53.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.53.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.53.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.53.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.53.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.54.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.54.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.54.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.54.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.54.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.54.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.55.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.55.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.55.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.55.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.55.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.55.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.56.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.56.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.56.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.56.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.56.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.56.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.57.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.57.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.57.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.57.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.57.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.57.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.58.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.58.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.58.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.58.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.58.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.58.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.59.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.59.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.59.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.59.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.59.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.59.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.6.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.6.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.6.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.60.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.60.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.60.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.60.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.60.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.60.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.61.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.61.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.61.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.61.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.61.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.61.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.62.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.62.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.62.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.62.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.62.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.62.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.63.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.63.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.63.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.63.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.63.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.63.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.64.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.64.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.64.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.64.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.64.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.64.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.65.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.65.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.65.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.65.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.65.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.65.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.66.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.66.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.66.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.66.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.66.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.66.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.67.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.67.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.67.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.67.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.67.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.67.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.68.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.68.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.68.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.68.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.68.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.68.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.69.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.69.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.69.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.69.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.69.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.69.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.7.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.7.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.7.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.70.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.70.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.70.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.70.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.70.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.70.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.71.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.71.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.71.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.71.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.71.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.71.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.72.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.72.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.72.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.72.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.72.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.72.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.73.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.73.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.73.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.73.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.73.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.73.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.74.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.74.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.74.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.74.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.74.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.74.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.75.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.75.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.75.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.75.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.75.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.75.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.76.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.76.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.76.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.76.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.76.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.76.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.77.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.77.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.77.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.77.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.77.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.77.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.78.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.78.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.78.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.78.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.78.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.78.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.79.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.79.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.79.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.79.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.79.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.79.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.8.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.8.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.8.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.8.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.8.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.8.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.80.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.80.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.80.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.80.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.80.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.80.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.81.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.81.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.81.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.81.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.81.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.81.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.82.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.82.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.82.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.82.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.82.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.82.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.83.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.83.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.83.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.83.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.83.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.83.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.84.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.84.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.84.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.84.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.84.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.84.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.85.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.85.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.85.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.85.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.85.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.85.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.86.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.86.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.86.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.86.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.86.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.86.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.87.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.87.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.87.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.87.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.87.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.87.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.88.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.88.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.88.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.88.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.88.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.88.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.89.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.89.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.89.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.89.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.89.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.89.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.9.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.9.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.9.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.9.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.9.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.9.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.90.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.90.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.90.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.90.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.90.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.90.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.91.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.91.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.91.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.91.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.91.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.91.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.92.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.92.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.92.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.92.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.92.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.92.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.93.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.93.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.93.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.93.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.93.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.93.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.94.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.94.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.94.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.94.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.94.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.94.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.95.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.95.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.95.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.95.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.95.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.95.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.96.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.96.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.96.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.96.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.96.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.96.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.97.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.97.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.97.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.97.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.97.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.97.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.98.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.98.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.98.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.98.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.98.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.98.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.99.w1.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.99.w1.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.99.w2.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.99.w2.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.99.w3.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.experts.99.w3.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.shared_experts.down_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.shared_experts.gate_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.shared_experts.up_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.post_attention_layernorm.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.index_k_norm.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.index_k_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.index_k_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.index_q_norm.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.index_q_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.index_q_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.k_norm.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.o_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.o_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.q_norm.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight": "model-00030-of-00059.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight_scale": "model-00030-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.e_score_correction_bias": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.e_score_correction_bias": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.0.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.0.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.0.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.1.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.1.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.1.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.10.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.10.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.10.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.100.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.100.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.100.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.101.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.101.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.101.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.102.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.102.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.102.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.103.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.103.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.103.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.104.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.104.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.104.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.105.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.105.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.105.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.106.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.106.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.106.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.107.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.107.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.107.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.0.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.0.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.0.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.1.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.1.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.1.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.10.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.10.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.10.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.100.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.100.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.100.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.101.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.101.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.101.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.102.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.102.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.102.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.103.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.103.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.103.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.104.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.104.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.104.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.105.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.105.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.105.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.106.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.106.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.106.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.107.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.107.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.107.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.108.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.108.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.108.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.108.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.108.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.108.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.109.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.109.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.109.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.109.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.109.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.109.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.11.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.11.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.11.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.110.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.110.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.110.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.110.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.110.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.110.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.111.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.111.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.111.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.111.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.111.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.111.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.112.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.112.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.112.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.112.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.112.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.112.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.113.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.113.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.113.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.113.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.113.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.113.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.114.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.114.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.114.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.114.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.114.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.114.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.115.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.115.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.115.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.115.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.115.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.115.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.116.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.116.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.116.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.116.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.116.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.116.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.117.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.117.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.117.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.117.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.117.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.117.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.118.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.118.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.118.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.118.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.118.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.118.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.119.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.119.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.119.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.119.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.119.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.119.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.12.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.12.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.12.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.120.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.120.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.120.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.120.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.120.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.120.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.121.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.121.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.121.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.121.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.121.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.121.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.122.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.122.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.122.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.122.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.122.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.122.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.123.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.123.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.123.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.123.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.123.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.123.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.124.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.124.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.124.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.124.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.124.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.124.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.125.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.125.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.125.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.125.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.125.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.125.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.126.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.126.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.126.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.126.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.126.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.126.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.127.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.127.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.127.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.127.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.127.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.127.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.13.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.13.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.13.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.14.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.14.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.14.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.15.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.15.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.15.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.16.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.16.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.16.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.17.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.17.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.17.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.18.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.18.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.18.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.19.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.19.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.19.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.2.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.2.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.2.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.20.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.20.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.20.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.21.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.21.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.21.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.22.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.22.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.22.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.23.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.23.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.23.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.24.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.24.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.24.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.25.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.25.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.25.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.26.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.26.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.26.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.27.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.27.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.27.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.28.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.28.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.28.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.29.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.29.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.29.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.3.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.3.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.3.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.30.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.30.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.30.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.31.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.31.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.31.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.32.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.32.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.32.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.33.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.33.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.33.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.34.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.34.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.34.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.35.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.35.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.35.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.36.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.36.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.36.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.37.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.37.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.37.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.38.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.38.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.38.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.39.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.39.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.39.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.4.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.4.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.4.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.40.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.40.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.40.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.41.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.41.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.41.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.42.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.42.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.42.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.43.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.43.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.43.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.44.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.44.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.44.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.45.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.45.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.45.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.46.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.46.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.46.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.47.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.47.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.47.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.48.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.48.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.48.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.49.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.49.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.49.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.5.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.5.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.5.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.50.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.50.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.50.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.51.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.51.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.51.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.52.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.52.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.52.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.53.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.53.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.53.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.54.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.54.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.54.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.55.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.55.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.55.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.56.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.56.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.56.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.57.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.57.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.57.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.58.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.58.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.58.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.59.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.59.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.59.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.6.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.6.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.6.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.60.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.60.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.60.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.61.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.61.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.61.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.62.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.62.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.62.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.63.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.63.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.63.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.64.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.64.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.64.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.64.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.64.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.64.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.65.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.65.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.65.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.65.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.65.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.65.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.66.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.66.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.66.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.66.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.66.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.66.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.67.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.67.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.67.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.67.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.67.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.67.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.68.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.68.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.68.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.68.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.68.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.68.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.69.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.69.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.69.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.69.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.69.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.69.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.7.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.7.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.7.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.70.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.70.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.70.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.70.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.70.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.70.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.71.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.71.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.71.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.71.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.71.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.71.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.72.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.72.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.72.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.72.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.72.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.72.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.73.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.73.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.73.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.73.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.73.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.73.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.74.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.74.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.74.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.74.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.74.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.74.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.75.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.75.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.75.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.75.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.75.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.75.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.76.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.76.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.76.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.76.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.76.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.76.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.77.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.77.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.77.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.77.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.77.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.77.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.78.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.78.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.78.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.78.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.78.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.78.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.79.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.79.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.79.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.79.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.79.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.79.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.8.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.8.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.8.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.80.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.80.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.80.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.80.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.80.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.80.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.81.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.81.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.81.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.81.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.81.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.81.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.82.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.82.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.82.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.82.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.83.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.83.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.83.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.84.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.84.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.84.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.85.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.85.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.85.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.86.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.86.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.86.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.87.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.87.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.87.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.88.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.88.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.88.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.89.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.89.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.89.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.9.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.9.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.9.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.90.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.90.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.90.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.90.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.91.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.91.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.91.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.91.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.91.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.91.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.92.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.92.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.92.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.92.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.92.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.92.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.93.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.93.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.93.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.93.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.93.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.93.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.94.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.94.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.94.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.94.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.94.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.94.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.95.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.95.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.95.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.95.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.95.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.95.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.96.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.96.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.96.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.96.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.96.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.96.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.97.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.97.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.97.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.97.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.97.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.97.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.98.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.98.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.98.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.98.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.98.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.98.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.99.w1.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.99.w1.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.99.w2.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.99.w2.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.99.w3.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.experts.99.w3.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.shared_experts.down_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.shared_experts.gate_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.shared_experts.up_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.index_k_norm.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.index_k_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.index_k_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.index_q_norm.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.index_q_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.index_q_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.k_norm.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.q_norm.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00059.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight_scale": "model-00004-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.gate.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.108.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.108.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.108.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.108.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.108.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.108.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.109.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.109.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.109.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.109.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.109.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.109.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.11.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.11.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.11.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.11.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.11.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.11.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.110.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.110.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.110.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.110.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.110.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.110.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.111.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.111.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.111.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.111.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.111.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.111.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.112.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.112.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.112.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.112.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.112.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.112.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.113.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.113.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.113.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.113.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.113.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.113.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.114.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.114.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.114.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.114.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.114.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.114.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.115.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.115.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.115.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.115.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.115.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.115.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.116.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.116.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.116.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.116.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.116.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.116.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.117.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.117.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.117.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.117.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.117.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.117.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.118.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.118.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.118.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.118.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.118.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.118.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.119.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.119.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.119.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.119.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.119.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.119.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.12.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.12.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.12.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.12.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.12.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.12.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.120.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.120.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.120.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.120.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.120.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.120.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.121.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.121.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.121.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.121.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.121.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.121.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.122.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.122.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.122.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.122.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.122.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.122.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.123.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.123.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.123.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.123.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.123.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.123.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.124.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.124.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.124.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.124.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.124.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.124.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.125.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.125.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.125.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.125.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.125.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.125.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.126.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.126.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.126.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.126.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.126.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.126.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.127.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.127.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.127.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.127.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.127.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.127.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.13.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.13.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.13.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.13.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.13.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.13.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.14.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.14.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.14.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.14.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.14.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.14.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.15.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.15.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.15.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.15.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.15.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.15.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.16.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.16.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.16.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.16.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.16.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.16.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.17.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.17.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.17.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.17.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.17.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.17.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.18.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.18.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.18.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.18.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.18.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.18.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.19.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.19.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.19.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.19.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.19.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.19.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.2.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.2.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.2.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.2.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.2.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.2.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.20.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.20.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.20.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.20.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.20.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.20.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.21.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.21.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.21.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.21.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.21.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.21.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.22.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.22.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.22.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.22.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.22.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.22.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.23.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.23.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.23.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.23.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.23.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.23.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.24.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.24.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.24.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.24.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.24.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.24.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.25.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.25.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.25.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.25.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.25.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.25.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.26.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.26.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.26.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.26.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.26.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.26.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.27.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.27.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.27.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.27.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.27.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.27.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.28.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.28.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.28.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.28.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.28.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.28.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.29.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.29.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.29.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.29.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.29.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.29.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.3.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.3.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.3.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.3.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.3.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.3.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.30.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.30.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.30.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.30.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.30.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.30.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.31.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.31.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.31.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.31.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.31.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.31.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.32.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.32.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.32.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.32.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.32.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.32.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.33.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.33.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.33.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.33.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.33.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.33.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.34.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.34.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.34.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.34.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.34.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.34.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.35.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.35.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.35.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.35.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.35.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.35.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.36.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.36.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.36.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.36.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.36.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.36.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.37.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.37.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.37.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.37.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.37.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.37.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.38.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.38.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.38.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.38.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.38.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.38.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.39.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.39.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.39.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.39.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.39.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.39.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.4.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.4.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.4.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.4.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.4.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.4.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.40.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.40.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.40.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.40.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.40.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.40.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.41.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.41.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.41.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.41.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.41.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.41.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.42.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.42.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.42.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.42.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.42.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.42.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.43.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.43.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.43.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.43.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.43.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.43.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.44.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.44.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.44.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.44.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.44.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.44.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.45.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.45.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.45.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.45.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.45.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.45.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.46.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.46.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.46.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.46.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.46.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.46.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.47.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.47.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.47.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.47.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.47.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.47.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.48.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.48.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.48.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.48.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.48.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.48.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.49.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.49.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.49.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.49.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.49.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.49.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.5.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.5.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.5.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.5.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.5.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.5.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.50.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.50.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.50.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.50.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.50.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.50.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.51.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.51.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.51.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.51.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.51.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.51.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.52.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.52.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.52.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.52.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.52.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.52.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.53.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.53.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.53.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.53.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.53.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.53.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.54.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.54.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.54.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.54.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.54.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.54.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.55.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.55.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.55.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.55.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.55.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.55.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.56.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.56.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.56.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.56.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.56.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.56.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.57.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.57.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.57.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.57.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.57.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.57.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.58.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.58.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.58.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.58.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.58.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.58.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.59.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.59.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.59.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.59.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.59.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.59.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.6.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.6.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.6.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.6.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.6.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.6.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.60.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.60.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.60.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.60.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.60.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.60.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.61.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.61.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.61.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.61.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.61.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.61.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.62.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.62.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.62.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.62.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.62.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.62.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.63.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.63.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.63.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.63.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.63.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.63.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.64.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.64.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.64.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.64.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.64.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.64.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.65.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.65.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.65.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.65.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.65.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.65.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.66.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.66.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.66.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.66.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.66.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.66.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.67.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.67.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.67.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.67.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.67.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.67.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.68.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.68.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.68.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.68.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.68.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.68.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.69.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.69.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.69.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.69.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.69.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.69.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.7.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.7.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.7.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.7.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.7.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.7.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.70.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.70.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.70.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.70.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.70.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.70.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.71.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.71.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.71.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.71.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.71.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.71.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.72.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.72.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.72.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.72.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.72.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.72.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.73.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.73.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.73.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.73.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.73.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.73.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.74.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.74.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.74.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.74.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.74.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.74.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.75.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.75.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.75.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.75.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.75.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.75.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.76.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.76.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.76.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.76.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.76.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.76.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.77.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.77.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.77.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.77.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.77.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.77.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.78.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.78.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.78.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.78.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.78.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.78.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.79.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.79.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.79.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.79.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.79.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.79.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.8.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.8.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.8.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.8.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.8.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.8.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.80.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.80.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.80.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.80.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.80.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.80.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.81.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.81.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.81.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.81.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.81.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.81.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.82.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.82.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.82.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.82.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.82.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.82.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.83.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.83.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.83.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.83.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.83.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.83.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.84.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.84.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.84.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.84.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.84.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.84.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.85.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.85.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.85.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.85.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.85.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.85.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.86.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.86.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.86.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.86.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.86.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.86.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.87.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.87.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.87.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.87.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.87.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.87.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.88.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.88.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.88.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.88.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.88.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.88.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.89.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.89.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.89.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.89.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.89.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.89.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.9.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.9.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.9.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.9.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.9.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.9.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.90.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.90.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.90.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.90.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.90.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.90.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.91.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.91.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.91.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.91.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.91.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.91.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.92.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.92.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.92.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.92.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.92.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.92.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.93.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.93.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.93.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.93.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.93.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.93.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.94.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.94.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.94.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.94.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.94.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.94.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.95.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.95.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.95.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.95.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.95.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.95.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.96.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.96.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.96.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.96.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.96.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.96.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.97.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.97.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.97.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.97.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.97.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.97.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.98.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.98.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.98.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.98.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.98.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.98.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.99.w1.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.99.w1.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.99.w2.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.99.w2.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.99.w3.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.99.w3.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.shared_experts.down_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.shared_experts.gate_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.shared_experts.up_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.input_layernorm.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.post_attention_layernorm.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.index_k_norm.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.index_k_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.index_k_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.index_q_norm.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.index_q_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.index_q_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.k_norm.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.k_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.k_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.o_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.o_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.q_norm.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.q_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.q_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.v_proj.weight": "model-00057-of-00059.safetensors", + "language_model.model.layers.57.self_attn.v_proj.weight_scale": "model-00057-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.e_score_correction_bias": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.gate.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.e_score_correction_bias": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.0.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.0.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.0.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.1.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.1.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.1.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.10.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.10.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.10.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.100.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.100.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.100.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.101.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.101.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.101.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.102.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.102.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.102.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.103.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.103.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.103.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.104.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.104.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.104.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.105.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.105.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.105.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.106.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.106.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.106.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.107.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.107.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.107.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.108.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.108.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.108.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.108.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.108.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.108.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.109.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.109.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.109.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.109.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.109.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.109.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.11.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.11.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.11.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.110.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.110.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.110.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.110.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.110.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.110.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.111.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.111.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.111.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.111.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.111.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.111.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.112.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.112.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.112.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.112.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.112.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.112.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.113.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.113.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.113.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.113.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.113.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.113.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.114.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.114.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.114.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.114.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.114.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.114.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.115.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.115.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.115.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.115.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.115.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.115.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.116.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.116.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.116.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.116.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.116.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.116.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.117.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.117.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.117.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.117.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.117.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.117.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.118.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.118.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.118.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.118.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.118.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.118.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.119.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.119.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.119.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.119.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.119.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.119.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.12.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.12.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.12.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.120.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.120.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.120.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.120.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.120.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.120.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.121.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.121.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.121.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.121.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.121.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.121.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.122.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.122.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.122.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.122.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.122.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.122.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.123.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.123.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.123.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.123.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.123.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.123.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.124.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.124.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.124.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.124.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.124.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.124.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.125.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.125.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.125.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.125.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.125.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.125.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.126.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.126.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.126.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.126.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.126.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.126.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.127.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.127.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.127.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.127.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.127.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.127.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.13.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.13.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.13.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.14.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.14.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.14.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.15.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.15.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.15.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.16.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.16.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.16.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.17.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.17.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.17.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.18.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.18.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.18.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.19.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.19.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.19.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.2.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.2.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.2.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.20.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.20.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.20.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.21.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.21.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.21.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.22.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.22.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.22.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.23.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.23.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.23.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.24.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.24.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.24.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.25.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.25.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.25.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.26.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.26.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.26.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.27.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.27.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.27.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.28.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.28.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.28.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.29.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.29.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.29.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.3.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.3.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.3.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.30.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.30.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.30.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.31.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.31.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.31.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.32.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.32.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.32.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.32.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.32.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.32.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.33.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.33.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.33.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.33.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.33.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.33.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.34.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.34.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.34.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.34.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.34.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.34.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.35.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.35.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.35.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.35.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.35.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.35.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.36.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.36.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.36.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.36.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.36.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.36.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.37.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.37.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.37.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.37.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.37.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.37.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.38.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.38.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.38.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.38.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.38.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.38.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.39.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.39.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.39.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.39.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.39.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.39.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.4.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.4.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.4.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.40.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.40.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.40.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.40.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.40.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.40.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.41.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.41.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.41.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.41.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.41.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.41.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.42.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.42.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.42.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.42.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.42.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.42.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.43.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.43.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.43.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.43.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.43.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.43.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.44.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.44.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.44.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.44.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.44.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.44.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.45.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.45.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.45.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.45.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.45.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.45.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.46.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.46.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.46.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.46.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.46.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.46.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.47.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.47.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.47.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.47.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.47.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.47.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.48.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.48.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.48.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.48.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.48.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.48.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.49.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.49.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.49.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.49.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.49.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.49.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.5.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.5.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.5.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.50.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.50.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.50.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.50.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.50.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.50.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.51.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.51.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.51.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.51.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.51.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.51.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.52.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.52.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.52.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.52.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.52.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.52.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.53.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.53.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.53.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.53.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.53.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.53.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.54.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.54.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.54.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.54.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.54.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.54.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.55.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.55.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.55.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.55.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.55.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.55.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.56.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.56.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.56.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.56.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.56.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.56.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.57.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.57.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.57.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.57.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.57.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.57.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.58.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.58.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.58.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.58.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.58.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.58.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.59.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.59.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.59.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.59.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.59.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.59.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.6.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.6.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.6.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.60.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.60.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.60.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.60.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.60.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.60.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.61.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.61.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.61.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.61.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.61.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.61.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.62.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.62.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.62.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.62.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.62.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.62.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.63.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.63.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.63.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.64.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.64.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.64.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.64.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.65.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.65.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.65.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.65.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.65.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.65.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.66.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.66.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.66.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.66.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.66.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.66.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.67.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.67.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.67.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.67.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.67.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.67.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.68.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.68.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.68.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.68.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.68.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.68.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.69.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.69.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.69.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.69.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.69.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.69.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.7.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.7.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.7.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.70.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.70.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.70.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.70.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.70.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.70.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.71.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.71.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.71.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.71.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.71.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.71.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.72.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.72.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.72.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.72.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.72.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.72.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.73.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.73.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.73.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.73.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.73.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.73.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.74.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.74.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.74.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.74.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.74.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.74.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.75.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.75.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.75.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.75.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.75.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.75.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.76.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.76.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.76.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.76.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.76.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.76.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.77.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.77.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.77.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.77.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.77.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.77.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.78.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.78.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.78.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.78.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.78.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.78.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.79.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.79.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.79.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.79.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.79.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.79.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.8.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.8.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.8.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.80.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.80.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.80.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.80.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.80.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.80.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.81.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.81.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.81.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.81.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.81.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.81.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.82.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.82.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.82.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.82.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.82.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.82.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.83.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.83.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.83.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.83.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.83.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.83.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.84.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.84.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.84.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.84.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.84.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.84.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.85.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.85.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.85.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.85.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.85.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.85.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.86.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.86.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.86.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.86.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.86.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.86.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.87.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.87.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.87.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.87.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.87.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.87.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.88.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.88.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.88.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.88.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.88.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.88.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.89.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.89.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.89.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.89.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.89.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.89.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.9.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.9.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.9.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.90.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.90.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.90.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.90.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.90.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.90.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.91.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.91.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.91.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.91.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.91.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.91.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.92.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.92.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.92.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.92.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.92.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.92.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.93.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.93.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.93.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.93.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.93.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.93.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.94.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.94.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.94.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.94.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.94.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.94.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.95.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.95.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.95.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.95.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.95.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.95.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.96.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.96.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.96.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.96.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.96.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.96.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.97.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.97.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.97.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.97.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.97.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.97.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.98.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.98.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.98.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.98.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.98.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.98.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.99.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.99.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.99.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.99.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.99.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.experts.99.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.shared_experts.down_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.shared_experts.gate_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.shared_experts.up_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.index_k_norm.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.index_k_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.index_k_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.index_q_norm.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.index_q_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.index_q_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.k_norm.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.q_norm.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.0.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.0.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.0.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.1.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.1.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.1.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.10.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.10.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.10.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.100.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.100.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.100.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.101.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.101.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.101.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.102.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.102.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.102.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.103.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.103.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.103.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.104.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.104.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.104.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.105.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.105.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.105.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.106.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.106.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.106.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.107.w1.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.107.w2.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.107.w3.weight_scale": "model-00014-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.e_score_correction_bias": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.k_norm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.q_norm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.k_norm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.q_norm.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.0.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.0.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.0.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.1.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.1.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.1.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.10.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.10.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.10.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.100.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.100.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.100.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.100.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.100.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.100.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.101.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.101.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.101.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.101.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.101.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.101.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.102.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.102.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.102.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.102.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.102.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.102.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.103.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.103.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.103.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.103.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.103.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.103.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.104.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.104.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.104.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.104.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.104.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.104.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.105.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.105.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.105.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.105.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.105.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.105.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.106.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.106.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.106.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.106.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.106.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.106.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.107.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.107.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.107.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.107.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.107.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.107.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.108.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.108.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.108.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.108.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.108.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.108.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.109.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.109.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.109.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.109.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.109.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.109.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.11.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.11.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.11.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.110.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.110.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.110.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.110.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.110.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.110.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.111.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.111.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.111.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.111.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.111.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.111.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.112.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.112.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.112.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.112.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.112.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.112.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.113.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.113.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.113.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.113.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.113.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.113.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.114.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.114.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.114.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.114.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.114.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.114.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.115.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.115.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.115.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.115.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.115.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.115.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.116.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.116.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.116.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.116.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.116.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.116.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.117.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.117.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.117.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.117.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.117.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.117.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.118.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.118.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.118.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.118.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.118.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.118.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.119.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.119.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.119.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.119.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.119.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.119.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.12.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.12.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.12.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.120.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.120.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.120.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.120.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.120.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.120.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.121.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.121.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.121.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.121.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.121.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.121.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.122.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.122.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.122.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.122.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.122.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.122.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.123.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.123.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.123.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.123.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.123.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.123.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.124.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.124.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.124.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.124.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.124.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.124.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.125.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.125.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.125.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.125.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.125.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.125.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.126.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.126.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.126.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.126.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.126.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.126.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.127.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.127.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.127.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.127.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.127.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.127.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.13.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.13.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.13.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.14.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.14.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.14.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.15.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.15.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.15.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.16.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.16.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.16.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.17.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.17.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.17.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.18.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.18.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.18.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.19.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.19.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.19.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.2.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.2.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.2.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.20.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.20.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.20.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.21.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.21.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.21.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.22.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.22.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.22.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.23.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.23.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.23.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.24.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.24.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.24.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.25.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.25.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.25.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.26.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.26.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.26.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.27.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.27.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.27.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.28.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.28.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.28.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.29.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.29.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.29.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.3.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.3.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.3.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.30.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.30.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.30.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.31.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.31.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.31.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.32.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.32.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.32.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.33.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.33.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.33.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.34.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.34.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.34.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.35.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.35.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.35.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.36.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.36.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.36.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.37.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.37.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.37.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.38.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.38.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.38.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.39.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.39.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.39.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.4.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.4.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.4.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.40.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.40.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.40.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.41.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.41.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.41.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.42.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.42.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.42.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.43.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.43.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.43.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.44.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.44.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.44.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.45.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.45.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.45.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.46.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.46.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.46.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.47.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.47.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.47.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.48.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.48.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.48.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.49.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.49.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.49.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.5.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.5.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.5.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.50.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.50.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.50.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.51.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.51.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.51.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.52.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.52.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.52.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.53.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.53.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.53.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.54.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.54.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.54.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.55.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.55.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.55.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.56.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.56.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.56.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.57.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.57.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.57.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.58.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.58.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.58.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.59.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.59.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.59.w3.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.6.w1.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.6.w2.weight_scale": "model-00002-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.6.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.60.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.60.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.60.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.60.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.60.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.60.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.61.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.61.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.61.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.61.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.61.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.61.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.62.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.62.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.62.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.62.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.62.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.62.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.63.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.63.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.63.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.63.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.63.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.63.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.64.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.64.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.64.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.64.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.64.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.64.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.65.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.65.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.65.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.65.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.65.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.65.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.66.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.66.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.66.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.66.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.66.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.66.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.67.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.67.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.67.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.67.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.67.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.67.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.68.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.68.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.68.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.68.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.68.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.68.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.69.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.69.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.69.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.69.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.69.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.69.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.7.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.7.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.7.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.70.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.70.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.70.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.70.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.70.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.70.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.71.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.71.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.71.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.71.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.71.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.71.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.72.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.72.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.72.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.72.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.72.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.72.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.73.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.73.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.73.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.73.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.73.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.73.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.74.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.74.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.74.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.74.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.74.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.74.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.75.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.75.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.75.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.75.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.75.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.75.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.76.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.76.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.76.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.76.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.76.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.76.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.77.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.77.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.77.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.77.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.77.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.77.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.78.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.78.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.78.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.78.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.78.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.78.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.79.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.79.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.79.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.79.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.79.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.79.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.8.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.8.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.8.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.8.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.8.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.8.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.80.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.80.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.80.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.80.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.80.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.80.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.81.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.81.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.81.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.81.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.81.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.81.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.82.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.82.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.82.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.82.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.82.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.82.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.83.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.83.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.83.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.83.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.83.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.83.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.84.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.84.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.84.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.84.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.84.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.84.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.85.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.85.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.85.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.85.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.85.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.85.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.86.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.86.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.86.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.86.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.86.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.86.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.87.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.87.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.87.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.87.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.87.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.87.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.88.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.88.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.88.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.88.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.88.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.88.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.89.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.89.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.89.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.89.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.89.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.89.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.9.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.9.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.9.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.9.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.9.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.9.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.90.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.90.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.90.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.90.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.90.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.90.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.91.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.91.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.91.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.91.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.91.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.91.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.92.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.92.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.92.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.92.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.92.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.92.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.93.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.93.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.93.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.93.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.93.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.93.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.94.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.94.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.94.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.94.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.94.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.94.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.95.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.95.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.95.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.95.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.95.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.95.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.96.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.96.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.96.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.96.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.96.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.96.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.97.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.97.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.97.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.97.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.97.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.97.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.98.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.98.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.98.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.98.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.98.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.98.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.99.w1.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.99.w1.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.99.w2.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.99.w2.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.99.w3.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.experts.99.w3.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.shared_experts.down_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.shared_experts.gate_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.shared_experts.up_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.index_k_norm.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.index_k_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.index_k_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.index_q_norm.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.index_q_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.index_q_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.k_norm.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.q_norm.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00025-of-00059.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight_scale": "model-00025-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.gate.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.108.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.108.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.108.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.108.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.108.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.108.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.109.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.109.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.109.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.109.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.109.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.109.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.11.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.11.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.11.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.11.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.11.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.11.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.110.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.110.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.110.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.110.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.110.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.110.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.111.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.111.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.111.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.111.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.111.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.111.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.112.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.112.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.112.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.112.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.112.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.112.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.113.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.113.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.113.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.113.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.113.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.113.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.114.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.114.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.114.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.114.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.114.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.114.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.115.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.115.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.115.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.115.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.115.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.115.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.116.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.116.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.116.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.116.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.116.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.116.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.117.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.117.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.117.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.117.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.117.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.117.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.118.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.118.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.118.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.118.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.118.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.118.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.119.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.119.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.119.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.119.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.119.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.119.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.12.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.12.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.12.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.12.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.12.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.12.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.120.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.120.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.120.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.120.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.120.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.120.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.121.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.121.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.121.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.121.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.121.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.121.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.122.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.122.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.122.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.122.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.122.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.122.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.123.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.123.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.123.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.123.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.123.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.123.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.124.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.124.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.124.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.124.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.124.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.124.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.125.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.125.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.125.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.125.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.125.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.125.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.126.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.126.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.126.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.126.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.126.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.126.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.127.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.127.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.127.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.127.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.127.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.127.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.13.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.13.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.13.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.13.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.13.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.13.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.14.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.14.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.14.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.14.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.14.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.14.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.15.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.15.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.15.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.15.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.15.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.15.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.16.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.16.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.16.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.16.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.16.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.16.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.17.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.17.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.17.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.17.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.17.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.17.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.18.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.18.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.18.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.18.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.18.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.18.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.19.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.19.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.19.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.19.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.19.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.19.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.2.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.2.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.2.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.20.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.20.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.20.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.20.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.20.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.20.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.21.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.21.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.21.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.21.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.21.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.21.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.22.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.22.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.22.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.22.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.22.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.22.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.23.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.23.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.23.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.23.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.23.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.23.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.24.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.24.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.24.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.24.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.24.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.24.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.25.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.25.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.25.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.25.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.25.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.25.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.26.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.26.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.26.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.26.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.26.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.26.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.27.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.27.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.27.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.27.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.27.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.27.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.28.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.28.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.28.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.28.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.28.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.28.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.29.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.29.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.29.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.29.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.29.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.29.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.3.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.3.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.3.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.30.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.30.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.30.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.30.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.30.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.30.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.31.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.31.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.31.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.31.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.31.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.31.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.32.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.32.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.32.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.32.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.32.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.32.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.33.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.33.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.33.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.33.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.33.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.33.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.34.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.34.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.34.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.34.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.34.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.34.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.35.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.35.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.35.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.35.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.35.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.35.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.36.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.36.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.36.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.36.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.36.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.36.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.37.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.37.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.37.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.37.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.37.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.37.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.38.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.38.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.38.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.38.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.38.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.38.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.39.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.39.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.39.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.39.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.39.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.39.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.4.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.4.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.4.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.4.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.40.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.40.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.40.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.40.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.40.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.40.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.41.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.41.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.41.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.41.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.41.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.41.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.42.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.42.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.42.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.42.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.42.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.42.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.43.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.43.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.43.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.43.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.43.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.43.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.44.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.44.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.44.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.44.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.44.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.44.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.45.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.45.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.45.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.45.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.45.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.45.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.46.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.46.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.46.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.46.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.46.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.46.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.47.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.47.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.47.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.47.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.47.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.47.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.48.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.48.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.48.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.48.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.48.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.48.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.49.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.49.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.49.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.49.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.49.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.49.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.5.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.5.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.5.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.50.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.50.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.50.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.50.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.50.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.50.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.51.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.51.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.51.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.51.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.51.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.51.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.52.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.52.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.52.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.52.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.52.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.52.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.53.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.53.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.53.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.53.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.53.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.53.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.54.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.54.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.54.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.54.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.54.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.54.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.55.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.55.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.55.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.55.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.55.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.55.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.56.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.56.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.56.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.56.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.56.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.56.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.57.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.57.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.57.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.57.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.57.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.57.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.58.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.58.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.58.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.58.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.58.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.58.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.59.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.59.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.59.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.59.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.59.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.59.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.6.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.6.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.6.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.60.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.60.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.60.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.60.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.60.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.60.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.61.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.61.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.61.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.61.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.61.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.61.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.62.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.62.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.62.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.62.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.62.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.62.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.63.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.63.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.63.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.63.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.63.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.63.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.64.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.64.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.64.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.64.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.64.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.64.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.65.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.65.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.65.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.65.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.65.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.65.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.66.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.66.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.66.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.66.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.66.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.66.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.67.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.67.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.67.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.67.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.67.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.67.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.68.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.68.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.68.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.68.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.68.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.68.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.69.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.69.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.69.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.69.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.69.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.69.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.7.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.7.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.7.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.70.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.70.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.70.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.70.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.70.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.70.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.71.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.71.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.71.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.71.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.71.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.71.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.72.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.72.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.72.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.72.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.72.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.72.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.73.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.73.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.73.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.73.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.73.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.73.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.74.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.74.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.74.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.74.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.74.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.74.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.75.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.75.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.75.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.75.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.75.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.75.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.76.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.76.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.76.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.76.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.76.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.76.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.77.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.77.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.77.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.77.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.77.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.77.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.78.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.78.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.78.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.78.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.78.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.78.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.79.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.79.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.79.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.79.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.79.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.79.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.8.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.8.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.8.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.8.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.8.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.8.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.80.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.80.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.80.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.80.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.80.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.80.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.81.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.81.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.81.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.81.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.81.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.81.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.82.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.82.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.82.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.82.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.82.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.82.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.83.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.83.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.83.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.83.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.83.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.83.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.84.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.84.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.84.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.84.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.84.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.84.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.85.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.85.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.85.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.85.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.85.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.85.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.86.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.86.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.86.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.86.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.86.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.86.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.87.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.87.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.87.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.87.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.87.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.87.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.88.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.88.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.88.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.88.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.88.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.88.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.89.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.89.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.89.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.89.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.89.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.89.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.9.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.9.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.9.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.9.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.9.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.9.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.90.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.90.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.90.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.90.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.90.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.90.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.91.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.91.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.91.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.91.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.91.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.91.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.92.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.92.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.92.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.92.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.92.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.92.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.93.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.93.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.93.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.93.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.93.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.93.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.94.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.94.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.94.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.94.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.94.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.94.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.95.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.95.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.95.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.95.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.95.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.95.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.96.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.96.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.96.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.96.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.96.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.96.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.97.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.97.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.97.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.97.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.97.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.97.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.98.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.98.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.98.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.98.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.98.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.98.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.99.w1.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.99.w1.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.99.w2.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.99.w2.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.99.w3.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.experts.99.w3.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.shared_experts.down_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.shared_experts.gate_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.shared_experts.up_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.input_layernorm.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.post_attention_layernorm.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.index_k_norm.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.index_k_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.index_k_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.index_q_norm.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.index_q_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.index_q_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.k_norm.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.q_norm.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight": "model-00039-of-00059.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight_scale": "model-00039-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.e_score_correction_bias": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.gate.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.e_score_correction_bias": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.0.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.0.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.0.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.1.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.1.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.1.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.10.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.10.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.10.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.10.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.10.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.10.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.100.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.100.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.100.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.100.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.100.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.100.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.101.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.101.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.101.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.101.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.101.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.101.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.102.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.102.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.102.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.102.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.102.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.102.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.103.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.103.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.103.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.103.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.103.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.103.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.104.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.104.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.104.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.104.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.104.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.104.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.105.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.105.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.105.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.105.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.105.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.105.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.106.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.106.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.106.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.106.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.106.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.106.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.107.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.107.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.107.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.107.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.107.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.107.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.108.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.108.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.108.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.108.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.108.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.108.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.109.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.109.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.109.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.109.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.109.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.109.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.11.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.11.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.11.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.11.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.11.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.11.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.110.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.110.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.110.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.110.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.110.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.110.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.111.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.111.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.111.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.111.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.111.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.111.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.112.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.112.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.112.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.112.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.112.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.112.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.113.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.113.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.113.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.113.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.113.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.113.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.114.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.114.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.114.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.114.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.114.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.114.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.115.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.115.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.115.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.115.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.115.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.115.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.116.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.116.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.116.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.116.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.116.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.116.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.117.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.117.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.117.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.117.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.117.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.117.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.118.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.118.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.118.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.118.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.118.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.118.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.119.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.119.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.119.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.119.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.119.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.119.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.12.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.12.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.12.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.12.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.12.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.12.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.120.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.120.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.120.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.120.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.120.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.120.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.121.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.121.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.121.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.121.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.121.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.121.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.122.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.122.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.122.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.122.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.122.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.122.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.123.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.123.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.123.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.123.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.123.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.123.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.124.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.124.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.124.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.124.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.124.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.124.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.125.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.125.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.125.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.125.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.125.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.125.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.126.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.126.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.126.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.126.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.126.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.126.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.127.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.127.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.127.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.127.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.127.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.127.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.13.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.13.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.13.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.13.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.13.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.13.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.14.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.14.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.14.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.14.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.14.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.14.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.15.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.15.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.15.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.15.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.15.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.15.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.16.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.16.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.16.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.16.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.16.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.16.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.17.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.17.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.17.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.17.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.17.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.17.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.18.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.18.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.18.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.18.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.18.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.18.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.19.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.19.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.19.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.19.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.19.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.19.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.2.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.2.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.2.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.20.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.20.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.20.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.20.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.20.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.20.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.21.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.21.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.21.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.21.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.21.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.21.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.22.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.22.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.22.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.22.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.22.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.22.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.23.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.23.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.23.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.23.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.23.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.23.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.24.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.24.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.24.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.24.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.24.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.24.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.25.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.25.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.25.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.25.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.25.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.25.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.26.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.26.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.26.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.26.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.26.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.26.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.27.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.27.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.27.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.27.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.27.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.27.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.28.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.28.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.28.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.28.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.28.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.28.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.29.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.29.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.29.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.29.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.29.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.29.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.3.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.3.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.3.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.30.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.30.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.30.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.30.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.30.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.30.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.31.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.31.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.31.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.31.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.31.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.31.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.32.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.32.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.32.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.32.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.32.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.32.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.33.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.33.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.33.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.33.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.33.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.33.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.34.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.34.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.34.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.34.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.34.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.34.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.35.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.35.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.35.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.35.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.35.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.35.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.36.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.36.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.36.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.36.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.36.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.36.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.37.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.37.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.37.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.37.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.37.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.37.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.38.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.38.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.38.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.38.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.38.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.38.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.39.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.39.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.39.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.39.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.39.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.39.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.4.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.4.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.4.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.40.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.40.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.40.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.40.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.40.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.40.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.41.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.41.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.41.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.41.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.41.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.41.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.42.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.42.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.42.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.42.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.42.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.42.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.43.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.43.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.43.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.43.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.43.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.43.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.44.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.44.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.44.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.44.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.44.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.44.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.45.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.45.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.45.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.45.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.45.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.45.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.46.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.46.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.46.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.46.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.46.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.46.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.47.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.47.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.47.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.47.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.47.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.47.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.48.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.48.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.48.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.48.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.48.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.48.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.49.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.49.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.49.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.49.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.49.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.49.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.5.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.5.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.5.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.50.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.50.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.50.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.50.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.50.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.50.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.51.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.51.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.51.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.51.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.51.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.51.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.52.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.52.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.52.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.52.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.52.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.52.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.53.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.53.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.53.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.53.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.53.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.53.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.54.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.54.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.54.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.54.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.54.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.54.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.55.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.55.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.55.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.55.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.55.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.55.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.56.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.56.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.56.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.56.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.56.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.56.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.57.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.57.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.57.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.57.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.57.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.57.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.58.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.58.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.58.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.58.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.58.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.58.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.59.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.59.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.59.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.59.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.59.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.59.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.6.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.6.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.6.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.60.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.60.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.60.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.60.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.60.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.60.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.61.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.61.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.61.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.61.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.61.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.61.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.62.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.62.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.62.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.62.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.62.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.62.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.63.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.63.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.63.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.63.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.63.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.63.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.64.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.64.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.64.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.64.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.64.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.64.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.65.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.65.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.65.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.65.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.65.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.65.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.66.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.66.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.66.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.66.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.66.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.66.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.67.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.67.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.67.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.67.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.67.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.67.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.68.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.68.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.68.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.68.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.68.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.68.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.69.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.69.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.69.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.69.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.69.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.69.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.7.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.7.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.7.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.70.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.70.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.70.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.70.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.70.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.70.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.71.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.71.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.71.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.71.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.71.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.71.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.72.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.72.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.72.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.72.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.72.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.72.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.73.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.73.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.73.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.73.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.73.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.73.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.74.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.74.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.74.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.74.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.74.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.74.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.75.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.75.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.75.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.75.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.75.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.75.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.76.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.76.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.76.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.76.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.76.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.76.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.77.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.77.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.77.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.77.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.77.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.77.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.78.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.78.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.78.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.78.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.78.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.78.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.79.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.79.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.79.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.79.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.79.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.79.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.8.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.8.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.8.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.8.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.8.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.8.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.80.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.80.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.80.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.80.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.80.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.80.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.81.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.81.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.81.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.81.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.81.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.81.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.82.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.82.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.82.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.82.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.82.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.82.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.83.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.83.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.83.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.83.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.83.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.83.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.84.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.84.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.84.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.84.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.84.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.84.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.85.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.85.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.85.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.85.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.85.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.85.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.86.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.86.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.86.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.86.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.86.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.86.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.87.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.87.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.87.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.87.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.87.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.87.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.88.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.88.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.88.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.88.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.88.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.88.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.89.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.89.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.89.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.89.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.89.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.89.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.9.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.9.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.9.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.9.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.9.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.9.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.90.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.90.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.90.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.90.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.90.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.90.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.91.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.91.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.91.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.91.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.91.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.91.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.92.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.92.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.92.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.92.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.92.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.92.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.93.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.93.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.93.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.93.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.93.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.93.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.94.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.94.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.94.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.94.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.94.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.94.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.95.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.95.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.95.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.95.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.95.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.95.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.96.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.96.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.96.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.96.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.96.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.96.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.97.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.97.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.97.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.97.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.97.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.97.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.98.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.98.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.98.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.98.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.98.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.98.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.99.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.99.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.99.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.99.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.99.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.experts.99.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.shared_experts.down_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.shared_experts.gate_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.shared_experts.up_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.index_k_norm.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.index_k_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.index_k_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.index_q_norm.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.index_q_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.index_q_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.k_norm.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.q_norm.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.0.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.0.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.0.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.1.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.1.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.1.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.10.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.10.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.10.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.10.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.10.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.10.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.100.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.100.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.100.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.100.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.100.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.100.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.101.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.101.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.101.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.101.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.101.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.101.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.102.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.102.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.102.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.102.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.102.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.102.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.103.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.103.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.103.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.103.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.103.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.103.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.104.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.104.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.104.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.104.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.104.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.104.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.105.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.105.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.105.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.105.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.105.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.105.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.106.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.106.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.106.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.106.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.106.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.106.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.107.w1.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.107.w1.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.107.w2.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.107.w2.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.107.w3.weight": "model-00022-of-00059.safetensors", + "language_model.model.layers.56.block_sparse_moe.experts.107.w3.weight_scale": "model-00022-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.e_score_correction_bias": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.gate.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.0.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.0.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.0.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.1.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.1.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.1.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.10.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.10.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.10.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.10.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.10.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.10.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.100.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.100.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.100.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.100.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.100.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.100.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.101.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.101.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.101.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.101.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.101.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.101.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.102.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.102.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.102.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.102.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.102.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.102.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.103.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.103.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.103.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.103.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.103.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.103.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.104.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.104.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.104.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.104.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.104.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.104.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.105.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.105.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.105.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.105.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.105.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.105.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.106.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.106.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.106.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.106.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.106.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.106.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.107.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.107.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.107.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.107.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.107.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.107.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.108.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.108.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.108.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.108.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.108.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.108.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.109.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.109.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.109.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.109.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.109.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.109.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.11.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.11.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.11.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.11.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.11.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.11.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.110.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.110.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.110.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.110.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.110.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.110.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.111.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.111.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.111.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.111.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.111.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.111.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.112.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.112.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.112.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.112.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.112.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.112.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.113.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.113.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.113.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.113.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.113.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.113.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.114.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.114.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.114.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.114.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.114.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.114.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.115.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.115.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.115.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.115.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.115.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.115.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.116.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.116.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.116.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.116.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.116.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.116.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.117.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.117.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.117.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.117.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.117.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.117.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.118.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.118.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.118.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.118.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.118.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.118.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.119.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.119.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.119.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.119.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.119.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.119.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.12.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.12.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.12.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.12.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.12.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.12.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.120.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.120.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.120.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.120.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.120.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.120.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.121.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.121.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.121.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.121.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.121.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.121.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.122.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.122.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.122.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.122.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.122.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.122.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.123.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.123.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.123.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.123.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.123.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.123.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.124.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.124.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.124.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.124.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.124.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.124.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.125.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.125.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.125.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.125.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.125.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.125.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.126.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.126.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.126.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.126.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.126.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.126.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.127.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.127.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.127.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.127.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.127.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.127.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.13.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.13.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.13.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.13.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.13.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.13.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.14.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.14.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.14.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.14.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.14.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.14.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.15.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.15.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.15.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.15.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.15.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.15.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.16.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.16.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.16.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.16.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.16.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.16.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.17.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.17.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.17.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.17.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.17.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.17.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.18.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.18.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.18.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.18.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.18.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.18.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.19.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.19.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.19.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.19.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.19.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.19.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.2.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.2.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.2.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.20.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.20.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.20.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.20.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.20.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.20.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.21.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.21.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.21.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.21.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.21.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.21.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.22.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.22.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.22.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.22.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.22.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.22.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.23.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.23.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.23.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.23.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.23.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.23.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.24.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.24.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.24.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.24.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.24.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.24.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.25.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.25.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.25.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.25.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.25.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.25.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.26.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.26.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.26.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.26.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.26.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.26.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.27.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.27.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.27.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.27.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.27.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.27.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.28.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.28.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.28.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.28.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.28.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.28.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.29.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.29.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.29.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.29.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.29.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.29.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.3.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.3.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.3.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.30.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.30.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.30.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.30.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.30.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.30.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.31.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.31.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.31.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.31.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.31.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.31.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.32.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.32.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.32.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.32.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.32.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.32.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.33.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.33.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.33.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.33.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.33.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.33.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.34.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.34.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.34.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.34.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.34.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.34.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.35.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.35.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.35.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.35.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.35.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.35.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.36.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.36.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.36.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.36.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.36.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.36.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.37.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.37.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.37.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.37.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.37.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.37.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.38.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.38.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.38.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.38.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.38.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.38.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.39.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.39.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.39.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.39.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.39.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.39.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.4.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.4.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.4.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.40.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.40.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.40.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.40.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.40.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.40.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.41.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.41.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.41.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.41.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.41.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.41.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.42.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.42.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.42.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.42.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.42.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.42.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.43.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.43.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.43.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.43.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.43.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.43.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.44.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.44.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.44.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.44.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.44.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.44.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.45.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.45.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.45.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.45.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.45.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.45.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.46.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.46.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.46.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.46.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.46.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.46.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.47.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.47.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.47.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.47.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.47.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.47.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.48.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.48.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.48.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.48.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.48.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.48.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.49.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.49.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.49.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.49.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.49.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.49.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.5.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.5.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.5.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.50.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.50.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.50.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.50.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.50.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.50.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.51.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.51.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.51.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.51.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.51.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.51.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.52.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.52.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.52.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.52.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.52.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.52.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.53.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.53.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.53.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.53.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.53.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.53.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.54.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.54.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.54.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.54.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.54.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.54.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.55.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.55.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.55.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.55.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.55.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.55.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.56.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.56.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.56.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.56.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.56.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.56.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.57.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.57.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.57.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.57.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.57.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.57.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.58.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.58.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.58.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.58.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.58.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.58.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.59.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.59.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.59.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.59.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.59.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.59.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.6.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.6.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.6.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.60.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.60.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.60.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.60.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.60.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.60.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.61.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.61.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.61.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.61.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.61.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.61.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.62.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.62.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.62.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.62.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.62.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.62.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.63.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.63.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.63.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.63.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.63.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.63.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.64.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.64.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.64.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.64.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.64.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.64.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.65.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.65.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.65.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.65.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.65.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.65.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.66.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.66.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.66.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.66.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.66.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.66.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.67.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.67.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.67.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.67.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.67.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.67.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.68.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.68.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.68.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.68.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.68.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.68.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.69.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.69.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.69.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.69.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.69.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.69.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.7.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.7.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.7.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.70.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.70.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.70.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.70.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.70.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.70.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.71.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.71.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.71.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.71.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.71.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.71.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.72.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.72.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.72.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.72.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.72.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.72.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.73.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.73.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.73.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.73.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.73.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.73.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.74.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.74.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.74.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.74.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.74.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.74.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.75.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.75.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.75.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.75.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.75.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.75.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.76.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.76.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.76.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.76.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.76.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.76.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.77.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.77.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.77.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.77.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.77.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.77.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.78.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.78.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.78.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.78.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.78.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.78.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.79.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.79.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.79.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.79.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.79.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.79.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.8.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.8.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.8.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.8.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.8.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.8.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.80.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.80.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.80.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.80.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.80.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.80.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.81.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.81.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.81.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.81.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.81.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.81.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.82.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.82.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.82.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.82.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.82.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.82.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.83.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.83.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.83.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.83.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.83.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.83.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.84.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.84.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.84.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.84.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.84.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.84.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.85.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.85.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.85.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.85.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.85.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.85.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.86.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.86.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.86.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.86.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.86.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.86.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.87.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.87.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.87.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.87.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.87.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.87.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.88.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.88.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.88.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.88.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.88.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.88.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.89.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.89.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.89.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.89.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.89.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.89.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.9.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.9.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.9.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.9.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.9.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.9.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.90.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.90.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.90.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.90.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.90.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.90.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.91.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.91.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.91.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.91.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.91.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.91.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.92.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.92.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.92.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.92.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.92.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.92.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.93.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.93.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.93.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.93.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.93.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.93.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.94.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.94.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.94.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.94.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.94.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.94.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.95.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.95.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.95.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.95.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.95.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.95.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.96.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.96.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.96.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.96.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.96.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.96.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.97.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.97.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.97.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.97.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.97.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.97.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.98.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.98.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.98.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.98.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.98.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.98.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.99.w1.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.99.w1.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.99.w2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.99.w2.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.99.w3.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.experts.99.w3.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.shared_experts.down_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.shared_experts.gate_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.shared_experts.up_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.index_k_norm.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.index_k_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.index_k_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.index_q_norm.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.index_q_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.index_q_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.k_norm.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.q_norm.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight_scale": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight_scale": "model-00026-of-00059.safetensors", + "multi_modal_projector.linear_1.weight": "model-00026-of-00059.safetensors", + "multi_modal_projector.linear_2.bias": "model-00026-of-00059.safetensors", + "multi_modal_projector.linear_2.weight": "model-00026-of-00059.safetensors", + "patch_merge_mlp.linear_1.bias": "model-00026-of-00059.safetensors", + "patch_merge_mlp.linear_1.weight": "model-00026-of-00059.safetensors", + "patch_merge_mlp.linear_2.bias": "model-00026-of-00059.safetensors", + "patch_merge_mlp.linear_2.weight": "model-00026-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.e_score_correction_bias": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.e_score_correction_bias": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.0.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.0.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.0.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.1.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.1.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.1.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.10.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.10.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.10.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.100.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.100.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.100.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.101.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.101.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.101.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.102.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.102.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.102.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.103.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.103.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.103.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.104.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.104.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.104.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.105.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.105.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.105.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.106.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.106.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.106.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.107.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.107.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.107.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.108.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.108.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.108.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.108.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.108.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.108.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.109.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.109.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.109.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.109.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.109.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.109.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.11.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.11.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.11.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.11.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.11.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.11.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.110.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.110.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.110.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.110.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.110.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.110.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.111.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.111.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.111.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.111.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.111.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.111.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.112.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.112.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.112.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.112.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.112.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.112.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.113.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.113.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.113.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.113.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.113.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.113.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.114.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.114.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.114.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.114.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.114.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.114.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.115.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.115.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.115.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.115.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.115.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.115.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.116.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.116.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.116.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.116.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.116.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.116.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.117.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.117.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.117.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.117.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.117.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.117.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.118.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.118.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.118.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.118.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.118.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.118.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.119.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.119.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.119.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.119.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.119.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.119.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.12.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.12.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.12.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.12.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.12.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.12.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.120.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.120.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.120.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.120.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.120.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.120.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.121.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.121.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.121.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.121.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.121.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.121.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.122.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.122.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.122.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.122.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.122.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.122.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.123.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.123.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.123.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.123.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.123.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.123.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.124.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.124.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.124.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.124.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.124.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.124.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.125.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.125.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.125.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.125.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.125.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.125.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.126.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.126.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.126.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.126.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.126.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.126.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.127.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.127.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.127.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.127.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.127.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.127.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.13.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.13.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.13.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.13.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.13.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.13.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.14.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.14.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.14.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.14.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.14.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.14.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.15.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.15.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.15.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.15.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.15.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.15.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.16.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.16.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.16.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.16.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.16.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.16.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.17.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.17.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.17.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.17.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.17.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.17.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.18.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.18.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.18.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.18.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.18.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.18.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.19.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.19.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.19.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.19.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.19.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.19.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.2.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.2.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.2.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.20.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.20.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.20.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.20.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.20.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.20.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.21.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.21.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.21.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.21.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.21.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.21.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.22.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.22.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.22.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.22.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.22.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.22.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.23.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.23.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.23.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.23.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.23.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.23.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.24.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.24.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.24.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.24.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.24.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.24.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.25.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.25.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.25.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.25.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.25.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.25.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.26.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.26.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.26.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.26.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.26.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.26.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.27.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.27.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.27.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.27.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.27.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.27.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.28.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.28.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.28.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.28.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.28.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.28.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.29.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.29.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.29.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.29.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.29.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.29.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.3.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.3.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.3.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.30.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.30.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.30.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.30.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.30.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.30.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.31.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.31.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.31.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.31.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.31.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.31.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.32.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.32.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.32.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.32.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.32.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.32.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.33.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.33.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.33.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.33.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.33.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.33.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.34.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.34.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.34.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.34.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.34.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.34.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.35.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.35.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.35.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.35.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.35.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.35.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.36.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.36.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.36.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.36.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.36.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.36.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.37.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.37.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.37.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.37.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.37.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.37.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.38.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.38.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.38.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.38.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.38.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.38.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.39.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.39.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.39.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.39.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.39.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.39.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.4.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.4.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.4.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.40.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.40.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.40.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.40.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.40.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.40.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.41.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.41.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.41.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.41.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.41.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.41.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.42.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.42.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.42.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.42.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.42.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.42.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.43.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.43.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.43.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.43.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.43.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.43.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.44.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.44.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.44.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.44.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.44.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.44.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.45.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.45.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.45.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.45.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.45.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.45.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.46.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.46.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.46.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.46.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.46.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.46.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.47.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.47.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.47.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.47.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.47.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.47.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.48.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.48.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.48.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.48.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.48.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.48.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.49.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.49.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.49.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.49.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.49.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.49.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.5.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.5.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.5.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.50.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.50.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.50.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.50.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.50.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.50.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.51.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.51.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.51.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.51.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.51.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.51.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.52.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.52.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.52.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.52.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.52.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.52.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.53.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.53.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.53.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.53.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.53.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.53.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.54.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.54.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.54.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.54.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.54.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.54.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.55.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.55.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.55.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.55.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.55.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.55.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.56.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.56.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.56.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.56.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.56.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.56.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.57.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.57.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.57.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.57.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.57.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.57.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.58.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.58.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.58.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.58.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.58.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.58.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.59.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.59.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.59.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.59.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.59.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.59.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.6.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.6.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.6.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.60.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.60.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.60.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.60.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.60.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.60.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.61.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.61.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.61.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.61.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.61.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.61.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.62.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.62.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.62.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.62.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.62.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.62.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.63.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.63.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.63.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.63.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.63.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.63.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.64.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.64.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.64.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.64.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.64.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.64.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.65.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.65.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.65.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.65.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.65.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.65.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.66.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.66.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.66.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.66.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.66.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.66.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.67.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.67.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.67.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.67.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.67.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.67.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.68.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.68.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.68.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.68.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.68.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.68.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.69.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.69.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.69.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.69.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.69.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.69.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.7.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.7.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.7.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.70.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.70.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.70.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.70.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.70.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.70.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.71.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.71.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.71.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.71.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.71.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.71.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.72.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.72.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.72.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.72.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.72.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.72.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.73.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.73.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.73.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.73.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.73.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.73.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.74.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.74.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.74.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.74.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.74.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.74.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.75.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.75.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.75.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.75.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.75.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.75.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.76.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.76.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.76.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.76.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.76.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.76.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.77.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.77.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.77.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.77.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.77.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.77.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.78.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.78.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.78.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.78.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.78.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.78.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.79.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.79.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.79.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.79.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.79.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.79.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.8.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.8.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.8.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.8.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.8.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.8.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.80.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.80.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.80.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.80.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.80.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.80.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.81.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.81.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.81.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.81.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.81.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.81.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.82.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.82.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.82.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.82.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.82.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.82.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.83.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.83.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.83.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.83.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.83.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.83.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.84.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.84.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.84.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.84.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.84.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.84.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.85.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.85.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.85.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.85.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.85.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.85.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.86.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.86.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.86.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.86.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.86.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.86.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.87.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.87.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.87.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.87.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.87.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.87.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.88.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.88.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.88.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.88.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.88.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.88.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.89.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.89.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.89.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.89.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.89.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.89.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.9.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.9.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.9.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.9.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.9.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.9.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.90.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.90.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.90.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.90.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.90.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.90.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.91.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.91.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.91.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.91.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.91.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.91.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.92.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.92.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.92.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.92.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.92.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.92.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.93.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.93.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.93.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.93.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.93.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.93.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.94.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.94.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.94.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.94.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.94.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.94.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.95.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.95.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.95.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.95.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.95.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.95.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.96.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.96.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.96.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.96.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.96.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.96.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.97.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.97.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.97.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.97.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.97.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.97.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.98.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.98.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.98.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.98.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.98.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.98.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.99.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.99.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.99.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.99.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.99.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.experts.99.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.shared_experts.down_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.shared_experts.gate_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.shared_experts.up_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.index_k_norm.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.index_k_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.index_k_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.index_q_norm.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.index_q_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.index_q_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.k_norm.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.q_norm.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.0.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.0.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.0.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.1.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.1.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.1.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.10.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.10.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.10.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.100.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.100.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.100.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.101.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.101.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.101.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.102.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.102.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.102.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.103.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.103.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.103.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.104.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.104.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.104.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.105.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.105.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.105.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.106.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.106.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.106.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.107.w1.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.107.w2.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00059.safetensors", + "language_model.model.layers.53.block_sparse_moe.experts.107.w3.weight_scale": "model-00019-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.e_score_correction_bias": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.gate.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.e_score_correction_bias": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.0.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.0.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.0.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.1.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.1.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.1.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.10.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.10.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.10.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.100.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.100.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.100.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.101.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.101.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.101.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.102.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.102.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.102.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.103.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.103.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.103.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.104.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.104.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.104.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.105.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.105.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.105.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.106.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.106.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.106.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.107.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.107.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.107.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.108.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.108.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.108.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.108.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.108.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.108.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.109.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.109.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.109.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.109.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.109.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.109.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.11.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.11.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.11.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.110.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.110.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.110.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.110.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.110.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.110.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.111.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.111.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.111.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.111.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.111.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.111.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.112.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.112.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.112.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.112.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.112.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.112.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.113.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.113.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.113.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.113.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.113.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.113.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.114.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.114.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.114.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.114.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.114.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.114.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.115.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.115.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.115.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.115.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.115.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.115.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.116.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.116.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.116.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.116.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.116.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.116.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.117.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.117.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.117.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.117.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.117.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.117.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.118.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.118.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.118.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.118.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.118.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.118.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.119.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.119.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.119.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.119.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.119.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.119.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.12.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.12.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.12.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.120.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.120.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.120.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.120.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.120.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.120.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.121.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.121.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.121.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.121.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.121.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.121.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.122.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.122.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.122.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.122.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.122.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.122.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.123.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.123.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.123.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.123.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.123.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.123.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.124.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.124.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.124.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.124.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.124.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.124.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.125.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.125.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.125.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.125.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.125.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.125.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.126.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.126.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.126.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.126.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.126.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.126.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.127.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.127.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.127.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.127.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.127.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.127.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.13.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.13.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.13.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.14.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.14.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.14.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.15.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.15.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.15.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.15.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.15.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.16.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.16.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.16.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.16.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.16.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.16.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.17.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.17.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.17.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.17.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.17.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.17.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.18.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.18.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.18.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.18.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.18.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.18.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.19.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.19.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.19.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.19.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.19.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.19.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.2.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.2.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.2.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.20.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.20.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.20.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.20.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.20.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.20.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.21.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.21.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.21.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.21.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.21.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.21.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.22.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.22.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.22.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.22.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.22.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.22.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.23.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.23.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.23.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.23.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.23.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.23.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.24.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.24.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.24.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.24.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.24.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.24.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.25.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.25.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.25.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.25.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.25.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.25.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.26.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.26.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.26.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.26.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.26.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.26.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.27.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.27.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.27.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.27.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.27.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.27.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.28.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.28.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.28.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.28.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.28.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.28.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.29.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.29.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.29.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.29.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.29.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.29.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.3.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.3.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.3.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.30.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.30.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.30.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.30.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.30.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.30.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.31.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.31.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.31.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.31.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.31.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.31.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.32.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.32.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.32.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.32.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.32.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.32.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.33.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.33.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.33.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.33.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.33.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.33.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.34.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.34.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.34.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.34.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.34.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.34.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.35.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.35.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.35.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.35.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.35.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.35.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.36.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.36.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.36.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.36.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.36.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.36.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.37.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.37.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.37.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.37.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.37.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.37.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.38.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.38.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.38.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.38.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.38.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.38.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.39.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.39.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.39.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.39.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.39.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.39.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.4.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.4.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.4.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.40.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.40.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.40.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.40.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.40.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.40.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.41.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.41.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.41.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.41.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.41.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.41.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.42.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.42.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.42.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.42.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.42.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.42.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.43.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.43.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.43.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.43.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.43.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.43.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.44.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.44.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.44.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.44.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.44.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.44.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.45.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.45.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.45.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.45.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.45.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.45.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.46.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.46.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.46.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.46.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.46.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.46.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.47.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.47.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.47.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.47.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.47.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.47.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.48.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.48.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.48.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.48.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.48.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.48.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.49.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.49.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.49.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.49.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.49.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.49.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.5.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.5.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.5.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.50.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.50.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.50.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.50.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.50.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.50.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.51.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.51.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.51.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.51.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.51.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.51.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.52.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.52.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.52.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.52.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.52.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.52.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.53.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.53.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.53.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.53.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.53.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.53.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.54.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.54.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.54.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.54.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.54.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.54.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.55.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.55.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.55.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.55.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.55.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.55.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.56.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.56.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.56.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.56.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.56.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.56.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.57.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.57.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.57.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.57.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.57.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.57.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.58.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.58.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.58.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.58.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.58.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.58.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.59.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.59.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.59.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.59.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.59.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.59.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.6.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.6.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.6.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.60.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.60.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.60.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.60.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.60.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.60.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.61.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.61.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.61.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.61.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.61.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.61.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.62.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.62.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.62.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.62.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.62.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.62.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.63.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.63.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.63.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.63.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.63.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.63.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.64.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.64.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.64.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.64.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.64.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.64.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.65.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.65.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.65.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.65.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.65.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.65.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.66.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.66.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.66.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.66.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.66.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.66.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.67.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.67.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.67.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.67.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.67.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.67.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.68.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.68.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.68.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.68.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.68.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.68.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.69.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.69.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.69.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.69.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.69.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.69.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.7.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.7.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.7.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.70.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.70.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.70.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.70.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.70.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.70.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.71.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.71.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.71.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.71.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.71.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.71.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.72.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.72.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.72.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.72.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.72.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.72.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.73.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.73.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.73.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.73.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.73.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.73.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.74.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.74.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.74.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.74.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.74.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.74.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.75.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.75.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.75.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.75.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.75.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.75.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.76.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.76.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.76.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.76.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.76.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.76.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.77.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.77.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.77.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.77.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.77.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.77.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.78.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.78.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.78.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.78.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.78.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.78.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.79.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.79.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.79.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.79.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.79.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.79.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.8.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.8.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.8.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.8.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.8.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.8.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.80.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.80.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.80.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.80.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.80.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.80.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.81.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.81.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.81.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.81.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.81.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.81.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.82.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.82.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.82.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.82.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.82.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.82.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.83.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.83.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.83.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.83.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.83.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.83.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.84.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.84.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.84.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.84.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.84.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.84.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.85.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.85.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.85.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.85.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.85.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.85.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.86.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.86.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.86.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.86.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.86.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.86.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.87.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.87.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.87.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.87.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.87.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.87.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.88.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.88.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.88.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.88.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.88.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.88.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.89.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.89.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.89.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.89.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.89.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.89.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.9.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.9.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.9.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.9.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.9.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.9.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.90.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.90.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.90.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.90.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.90.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.90.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.91.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.91.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.91.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.91.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.91.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.91.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.92.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.92.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.92.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.92.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.92.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.92.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.93.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.93.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.93.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.93.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.93.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.93.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.94.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.94.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.94.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.94.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.94.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.94.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.95.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.95.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.95.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.95.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.95.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.95.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.96.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.96.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.96.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.96.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.96.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.96.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.97.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.97.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.97.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.97.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.97.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.97.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.98.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.98.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.98.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.98.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.98.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.98.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.99.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.99.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.99.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.99.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.99.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.experts.99.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.shared_experts.down_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.shared_experts.gate_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.shared_experts.up_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.index_k_norm.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.index_k_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.index_k_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.index_q_norm.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.index_q_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.index_q_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.k_norm.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.q_norm.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.0.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.0.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.0.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.1.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.1.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.1.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.10.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.10.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.10.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.100.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.100.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.100.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.101.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.101.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.101.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.102.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.102.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.102.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.103.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.103.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.103.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.104.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.104.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.104.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.105.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.105.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.105.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.106.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.106.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.106.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.107.w1.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.107.w2.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.107.w3.weight_scale": "model-00017-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.e_score_correction_bias": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.gate.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.e_score_correction_bias": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.0.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.0.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.0.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.1.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.1.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.1.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.10.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.10.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.10.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.10.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.10.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.10.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.100.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.100.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.100.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.100.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.100.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.100.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.101.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.101.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.101.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.101.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.101.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.101.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.102.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.102.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.102.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.102.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.102.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.102.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.103.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.103.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.103.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.103.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.103.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.103.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.104.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.104.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.104.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.104.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.104.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.104.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.105.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.105.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.105.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.105.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.105.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.105.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.106.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.106.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.106.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.106.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.106.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.106.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.107.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.107.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.107.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.107.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.107.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.107.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.108.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.108.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.108.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.108.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.108.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.108.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.109.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.109.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.109.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.109.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.109.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.109.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.11.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.11.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.11.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.11.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.11.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.11.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.110.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.110.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.110.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.110.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.110.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.110.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.111.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.111.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.111.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.111.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.111.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.111.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.112.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.112.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.112.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.112.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.112.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.112.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.113.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.113.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.113.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.113.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.113.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.113.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.114.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.114.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.114.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.114.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.114.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.114.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.115.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.115.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.115.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.115.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.115.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.115.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.116.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.116.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.116.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.116.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.116.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.116.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.117.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.117.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.117.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.117.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.117.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.117.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.118.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.118.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.118.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.118.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.118.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.118.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.119.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.119.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.119.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.119.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.119.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.119.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.12.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.12.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.12.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.12.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.12.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.12.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.120.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.120.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.120.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.120.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.120.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.120.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.121.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.121.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.121.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.121.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.121.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.121.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.122.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.122.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.122.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.122.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.122.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.122.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.123.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.123.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.123.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.123.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.123.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.123.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.124.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.124.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.124.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.124.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.124.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.124.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.125.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.125.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.125.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.125.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.125.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.125.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.126.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.126.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.126.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.126.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.126.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.126.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.127.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.127.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.127.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.127.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.127.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.127.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.13.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.13.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.13.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.13.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.13.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.13.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.14.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.14.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.14.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.14.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.14.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.14.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.15.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.15.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.15.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.15.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.15.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.15.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.16.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.16.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.16.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.16.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.16.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.16.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.17.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.17.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.17.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.17.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.17.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.17.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.18.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.18.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.18.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.18.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.18.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.18.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.19.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.19.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.19.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.19.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.19.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.19.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.2.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.2.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.2.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.20.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.20.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.20.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.20.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.20.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.20.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.21.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.21.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.21.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.21.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.21.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.21.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.22.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.22.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.22.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.22.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.22.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.22.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.23.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.23.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.23.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.23.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.23.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.23.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.24.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.24.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.24.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.24.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.24.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.24.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.25.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.25.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.25.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.25.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.25.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.25.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.26.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.26.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.26.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.26.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.26.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.26.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.27.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.27.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.27.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.27.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.27.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.27.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.28.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.28.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.28.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.28.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.28.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.28.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.29.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.29.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.29.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.29.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.29.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.29.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.3.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.3.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.3.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.30.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.30.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.30.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.30.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.30.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.30.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.31.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.31.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.31.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.31.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.31.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.31.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.32.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.32.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.32.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.32.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.32.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.32.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.33.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.33.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.33.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.33.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.33.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.33.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.34.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.34.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.34.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.34.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.34.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.34.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.35.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.35.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.35.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.35.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.35.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.35.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.36.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.36.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.36.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.36.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.36.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.36.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.37.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.37.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.37.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.37.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.37.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.37.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.38.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.38.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.38.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.38.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.38.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.38.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.39.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.39.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.39.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.39.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.39.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.39.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.4.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.4.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.4.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.40.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.40.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.40.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.40.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.40.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.40.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.41.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.41.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.41.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.41.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.41.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.41.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.42.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.42.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.42.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.42.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.42.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.42.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.43.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.43.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.43.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.43.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.43.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.43.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.44.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.44.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.44.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.44.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.44.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.44.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.45.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.45.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.45.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.45.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.45.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.45.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.46.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.46.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.46.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.46.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.46.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.46.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.47.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.47.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.47.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.47.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.47.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.47.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.48.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.48.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.48.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.48.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.48.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.48.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.49.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.49.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.49.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.49.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.49.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.49.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.5.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.5.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.5.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.50.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.50.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.50.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.50.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.50.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.50.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.51.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.51.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.51.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.51.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.51.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.51.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.52.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.52.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.52.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.52.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.52.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.52.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.53.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.53.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.53.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.53.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.53.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.53.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.54.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.54.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.54.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.54.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.54.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.54.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.55.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.55.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.55.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.55.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.55.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.55.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.56.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.56.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.56.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.56.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.56.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.56.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.57.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.57.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.57.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.57.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.57.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.57.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.58.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.58.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.58.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.58.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.58.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.58.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.59.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.59.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.59.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.59.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.59.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.59.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.6.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.6.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.6.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.60.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.60.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.60.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.60.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.60.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.60.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.61.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.61.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.61.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.61.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.61.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.61.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.62.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.62.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.62.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.62.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.62.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.62.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.63.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.63.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.63.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.63.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.63.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.63.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.64.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.64.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.64.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.64.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.64.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.64.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.65.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.65.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.65.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.65.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.65.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.65.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.66.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.66.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.66.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.66.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.66.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.66.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.67.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.67.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.67.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.67.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.67.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.67.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.68.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.68.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.68.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.68.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.68.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.68.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.69.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.69.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.69.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.69.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.69.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.69.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.7.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.7.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.7.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.70.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.70.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.70.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.70.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.70.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.70.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.71.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.71.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.71.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.71.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.71.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.71.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.72.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.72.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.72.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.72.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.72.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.72.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.73.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.73.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.73.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.73.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.73.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.73.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.74.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.74.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.74.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.74.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.74.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.74.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.75.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.75.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.75.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.75.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.75.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.75.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.76.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.76.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.76.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.76.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.76.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.76.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.77.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.77.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.77.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.77.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.77.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.77.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.78.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.78.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.78.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.78.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.78.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.78.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.79.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.79.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.79.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.79.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.79.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.79.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.8.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.8.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.8.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.8.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.8.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.8.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.80.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.80.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.80.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.80.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.80.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.80.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.81.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.81.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.81.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.81.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.81.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.81.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.82.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.82.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.82.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.82.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.82.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.82.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.83.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.83.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.83.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.83.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.83.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.83.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.84.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.84.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.84.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.84.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.84.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.84.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.85.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.85.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.85.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.85.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.85.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.85.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.86.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.86.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.86.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.86.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.86.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.86.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.87.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.87.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.87.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.87.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.87.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.87.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.88.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.88.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.88.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.88.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.88.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.88.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.89.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.89.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.89.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.89.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.89.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.89.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.9.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.9.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.9.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.9.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.9.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.9.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.90.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.90.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.90.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.90.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.90.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.90.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.91.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.91.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.91.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.91.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.91.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.91.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.92.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.92.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.92.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.92.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.92.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.92.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.93.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.93.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.93.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.93.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.93.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.93.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.94.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.94.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.94.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.94.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.94.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.94.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.95.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.95.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.95.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.95.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.95.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.95.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.96.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.96.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.96.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.96.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.96.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.96.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.97.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.97.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.97.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.97.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.97.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.97.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.98.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.98.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.98.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.98.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.98.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.98.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.99.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.99.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.99.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.99.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.99.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.experts.99.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.shared_experts.down_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.shared_experts.gate_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.shared_experts.up_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.index_k_norm.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.index_k_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.index_k_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.index_q_norm.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.index_q_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.index_q_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.k_norm.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.q_norm.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.0.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.0.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.0.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.1.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.1.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.1.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.10.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.10.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.10.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.10.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.10.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.10.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.100.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.100.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.100.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.100.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.100.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.100.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.101.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.101.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.101.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.101.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.101.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.101.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.102.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.102.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.102.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.102.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.102.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.102.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.103.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.103.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.103.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.103.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.103.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.103.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.104.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.104.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.104.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.104.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.104.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.104.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.105.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.105.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.105.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.105.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.105.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.105.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.106.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.106.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.106.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.106.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.106.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.106.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.107.w1.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.107.w1.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.107.w2.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.107.w2.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.107.w3.weight": "model-00024-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.107.w3.weight_scale": "model-00024-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.gate.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.108.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.108.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.108.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.108.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.108.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.108.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.109.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.109.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.109.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.109.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.109.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.109.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.11.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.11.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.11.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.11.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.11.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.11.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.110.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.110.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.110.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.110.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.110.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.110.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.111.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.111.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.111.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.111.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.111.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.111.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.112.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.112.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.112.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.112.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.112.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.112.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.113.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.113.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.113.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.113.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.113.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.113.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.114.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.114.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.114.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.114.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.114.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.114.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.115.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.115.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.115.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.115.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.115.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.115.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.116.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.116.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.116.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.116.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.116.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.116.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.117.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.117.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.117.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.117.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.117.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.117.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.118.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.118.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.118.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.118.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.118.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.118.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.119.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.119.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.119.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.119.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.119.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.119.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.12.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.12.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.12.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.12.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.12.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.12.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.120.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.120.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.120.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.120.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.120.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.120.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.121.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.121.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.121.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.121.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.121.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.121.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.122.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.122.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.122.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.122.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.122.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.122.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.123.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.123.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.123.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.123.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.123.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.123.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.124.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.124.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.124.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.124.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.124.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.124.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.125.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.125.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.125.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.125.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.125.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.125.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.126.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.126.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.126.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.126.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.126.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.126.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.127.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.127.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.127.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.127.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.127.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.127.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.13.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.13.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.13.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.13.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.13.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.13.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.14.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.14.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.14.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.14.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.14.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.14.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.15.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.15.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.15.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.15.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.15.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.15.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.16.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.16.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.16.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.16.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.16.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.16.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.17.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.17.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.17.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.17.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.17.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.17.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.18.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.18.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.18.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.18.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.18.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.18.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.19.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.19.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.19.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.19.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.19.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.19.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.2.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.2.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.2.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.20.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.20.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.20.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.20.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.20.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.20.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.21.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.21.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.21.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.21.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.21.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.21.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.22.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.22.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.22.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.22.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.22.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.22.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.23.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.23.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.23.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.23.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.23.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.23.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.24.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.24.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.24.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.24.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.24.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.24.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.25.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.25.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.25.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.25.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.25.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.25.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.26.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.26.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.26.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.26.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.26.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.26.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.27.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.27.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.27.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.27.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.27.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.27.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.28.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.28.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.28.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.28.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.28.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.28.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.29.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.29.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.29.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.29.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.29.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.29.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.3.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.3.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.3.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.30.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.30.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.30.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.30.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.30.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.30.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.31.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.31.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.31.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.31.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.31.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.31.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.32.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.32.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.32.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.32.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.32.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.32.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.33.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.33.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.33.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.33.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.33.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.33.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.34.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.34.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.34.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.34.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.34.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.34.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.35.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.35.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.35.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.35.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.35.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.35.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.36.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.36.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.36.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.36.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.36.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.36.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.37.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.37.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.37.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.37.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.37.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.37.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.38.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.38.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.38.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.38.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.38.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.38.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.39.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.39.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.39.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.39.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.39.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.39.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.4.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.4.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.4.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.4.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.4.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.4.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.40.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.40.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.40.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.40.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.40.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.40.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.41.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.41.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.41.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.41.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.41.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.41.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.42.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.42.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.42.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.42.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.42.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.42.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.43.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.43.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.43.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.43.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.43.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.43.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.44.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.44.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.44.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.44.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.44.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.44.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.45.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.45.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.45.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.45.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.45.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.45.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.46.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.46.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.46.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.46.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.46.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.46.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.47.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.47.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.47.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.47.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.47.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.47.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.48.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.48.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.48.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.48.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.48.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.48.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.49.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.49.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.49.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.49.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.49.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.49.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.5.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.5.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.5.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.50.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.50.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.50.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.50.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.50.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.50.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.51.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.51.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.51.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.51.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.51.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.51.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.52.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.52.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.52.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.52.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.52.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.52.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.53.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.53.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.53.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.53.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.53.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.53.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.54.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.54.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.54.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.54.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.54.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.54.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.55.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.55.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.55.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.55.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.55.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.55.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.56.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.56.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.56.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.56.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.56.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.56.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.57.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.57.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.57.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.57.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.57.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.57.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.58.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.58.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.58.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.58.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.58.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.58.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.59.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.59.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.59.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.59.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.59.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.59.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.6.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.6.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.6.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.60.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.60.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.60.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.60.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.60.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.60.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.61.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.61.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.61.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.61.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.61.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.61.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.62.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.62.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.62.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.62.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.62.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.62.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.63.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.63.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.63.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.63.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.63.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.63.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.64.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.64.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.64.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.64.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.64.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.64.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.65.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.65.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.65.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.65.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.65.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.65.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.66.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.66.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.66.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.66.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.66.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.66.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.67.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.67.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.67.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.67.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.67.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.67.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.68.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.68.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.68.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.68.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.68.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.68.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.69.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.69.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.69.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.69.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.69.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.69.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.7.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.7.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.7.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.70.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.70.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.70.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.70.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.70.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.70.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.71.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.71.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.71.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.71.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.71.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.71.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.72.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.72.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.72.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.72.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.72.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.72.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.73.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.73.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.73.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.73.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.73.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.73.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.74.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.74.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.74.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.74.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.74.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.74.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.75.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.75.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.75.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.75.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.75.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.75.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.76.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.76.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.76.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.76.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.76.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.76.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.77.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.77.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.77.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.77.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.77.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.77.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.78.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.78.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.78.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.78.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.78.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.78.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.79.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.79.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.79.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.79.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.79.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.79.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.8.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.8.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.8.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.8.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.8.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.8.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.80.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.80.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.80.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.80.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.80.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.80.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.81.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.81.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.81.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.81.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.81.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.81.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.82.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.82.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.82.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.82.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.82.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.82.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.83.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.83.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.83.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.83.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.83.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.83.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.84.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.84.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.84.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.84.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.84.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.84.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.85.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.85.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.85.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.85.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.85.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.85.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.86.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.86.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.86.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.86.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.86.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.86.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.87.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.87.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.87.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.87.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.87.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.87.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.88.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.88.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.88.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.88.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.88.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.88.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.89.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.89.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.89.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.89.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.89.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.89.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.9.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.9.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.9.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.9.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.9.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.9.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.90.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.90.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.90.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.90.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.90.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.90.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.91.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.91.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.91.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.91.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.91.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.91.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.92.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.92.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.92.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.92.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.92.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.92.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.93.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.93.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.93.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.93.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.93.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.93.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.94.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.94.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.94.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.94.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.94.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.94.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.95.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.95.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.95.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.95.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.95.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.95.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.96.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.96.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.96.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.96.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.96.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.96.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.97.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.97.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.97.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.97.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.97.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.97.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.98.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.98.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.98.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.98.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.98.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.98.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.99.w1.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.99.w1.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.99.w2.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.99.w2.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.99.w3.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.99.w3.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.shared_experts.down_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.shared_experts.gate_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.shared_experts.up_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.input_layernorm.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.post_attention_layernorm.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.index_k_norm.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.index_k_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.index_k_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.index_q_norm.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.index_q_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.index_q_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.k_norm.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.k_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.k_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.o_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.o_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.q_norm.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.q_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.q_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.v_proj.weight": "model-00040-of-00059.safetensors", + "language_model.model.layers.40.self_attn.v_proj.weight_scale": "model-00040-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.e_score_correction_bias": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.e_score_correction_bias": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.0.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.0.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.0.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.1.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.1.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.1.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.10.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.10.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.10.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.100.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.100.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.100.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.101.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.101.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.101.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.102.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.102.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.102.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.103.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.103.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.103.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.104.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.104.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.104.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.105.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.105.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.105.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.106.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.106.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.106.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.107.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.107.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.107.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.108.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.108.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.108.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.108.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.108.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.108.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.109.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.109.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.109.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.109.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.109.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.109.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.11.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.11.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.11.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.110.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.110.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.110.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.110.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.110.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.110.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.111.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.111.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.111.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.111.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.111.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.111.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.112.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.112.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.112.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.112.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.112.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.112.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.113.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.113.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.113.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.113.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.113.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.113.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.114.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.114.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.114.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.114.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.114.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.114.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.115.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.115.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.115.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.115.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.115.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.115.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.116.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.116.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.116.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.116.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.116.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.116.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.117.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.117.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.117.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.117.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.117.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.117.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.118.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.118.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.118.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.118.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.118.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.118.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.119.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.119.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.119.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.119.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.119.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.119.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.12.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.12.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.12.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.120.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.120.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.120.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.120.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.120.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.120.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.121.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.121.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.121.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.121.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.121.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.121.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.122.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.122.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.122.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.122.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.122.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.122.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.123.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.123.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.123.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.123.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.123.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.123.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.124.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.124.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.124.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.124.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.124.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.124.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.125.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.125.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.125.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.125.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.125.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.125.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.126.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.126.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.126.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.126.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.126.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.126.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.127.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.127.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.127.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.127.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.127.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.127.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.13.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.13.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.13.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.14.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.14.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.14.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.15.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.15.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.15.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.16.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.16.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.16.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.17.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.17.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.17.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.18.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.18.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.18.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.19.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.19.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.19.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.2.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.2.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.2.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.20.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.20.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.20.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.21.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.21.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.21.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.22.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.22.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.22.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.23.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.23.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.23.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.24.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.24.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.24.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.25.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.25.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.25.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.26.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.26.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.26.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.27.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.27.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.27.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.28.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.28.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.28.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.29.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.29.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.29.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.3.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.3.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.3.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.30.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.30.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.30.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.31.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.31.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.31.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.32.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.32.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.32.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.33.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.33.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.33.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.34.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.34.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.34.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.34.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.35.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.35.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.35.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.36.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.36.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.36.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.37.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.37.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.37.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.38.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.38.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.38.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.38.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.39.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.39.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.39.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.4.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.4.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.4.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.40.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.40.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.40.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.41.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.41.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.41.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.42.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.42.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.42.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.43.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.43.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.43.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.44.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.44.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.44.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.45.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.45.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.45.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.46.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.46.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.46.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.47.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.47.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.47.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.48.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.48.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.48.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.49.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.49.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.49.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.5.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.5.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.5.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.50.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.50.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.50.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.51.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.51.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.51.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.52.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.52.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.52.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.53.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.53.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.53.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.54.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.54.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.54.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.55.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.55.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.55.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.56.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.56.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.56.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.57.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.57.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.57.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.58.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.58.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.58.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.59.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.59.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.59.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.6.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.6.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.6.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.60.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.60.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.60.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.61.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.61.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.61.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.62.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.62.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.62.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.63.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.63.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.63.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.64.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.64.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.64.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.65.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.65.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.65.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.66.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.66.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.66.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.67.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.67.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.67.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.67.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.67.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.67.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.68.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.68.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.68.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.68.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.68.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.68.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.69.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.69.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.69.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.69.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.69.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.69.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.7.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.7.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.7.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.70.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.70.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.70.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.70.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.70.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.70.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.71.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.71.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.71.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.71.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.71.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.71.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.72.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.72.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.72.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.72.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.72.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.72.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.73.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.73.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.73.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.73.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.73.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.73.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.74.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.74.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.74.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.74.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.74.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.74.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.75.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.75.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.75.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.75.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.75.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.75.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.76.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.76.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.76.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.76.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.76.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.76.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.77.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.77.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.77.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.77.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.77.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.77.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.78.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.78.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.78.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.78.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.78.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.78.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.79.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.79.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.79.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.79.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.79.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.79.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.8.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.8.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.8.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.80.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.80.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.80.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.80.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.80.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.80.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.81.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.81.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.81.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.81.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.81.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.81.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.82.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.82.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.82.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.82.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.82.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.82.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.83.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.83.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.83.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.83.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.83.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.83.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.84.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.84.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.84.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.84.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.84.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.84.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.85.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.85.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.85.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.85.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.85.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.85.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.86.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.86.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.86.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.86.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.86.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.86.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.87.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.87.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.87.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.87.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.87.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.87.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.88.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.88.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.88.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.88.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.88.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.88.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.89.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.89.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.89.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.89.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.89.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.89.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.9.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.9.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.9.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.90.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.90.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.90.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.90.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.90.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.90.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.91.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.91.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.91.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.91.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.91.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.91.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.92.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.92.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.92.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.92.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.92.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.92.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.93.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.93.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.93.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.93.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.93.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.93.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.94.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.94.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.94.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.94.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.94.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.94.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.95.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.95.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.95.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.95.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.95.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.95.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.96.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.96.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.96.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.96.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.96.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.96.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.97.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.97.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.97.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.97.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.97.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.97.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.98.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.98.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.98.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.98.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.98.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.98.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.99.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.99.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.99.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.99.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.99.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.experts.99.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.shared_experts.down_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.shared_experts.gate_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.shared_experts.up_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.index_k_norm.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.index_k_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.index_k_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.index_q_norm.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.index_q_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.index_q_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.k_norm.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.q_norm.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.0.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.0.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.0.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.1.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.1.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.1.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.10.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.10.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.10.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.100.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.100.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.100.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.101.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.101.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.101.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.102.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.102.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.102.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.103.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.103.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.103.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.104.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.104.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.104.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.105.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.105.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.105.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.106.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.106.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.106.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.107.w1.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.107.w2.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.107.w3.weight_scale": "model-00003-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.e_score_correction_bias": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.e_score_correction_bias": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.0.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.0.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.0.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.1.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.1.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.1.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.10.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.10.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.10.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.100.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.100.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.100.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.101.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.101.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.101.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.102.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.102.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.102.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.103.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.103.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.103.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.104.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.104.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.104.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.105.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.105.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.105.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.106.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.106.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.106.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.107.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.107.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.107.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.0.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.0.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.0.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.1.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.1.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.1.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.10.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.10.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.10.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.100.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.100.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.100.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.101.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.101.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.101.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.102.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.102.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.102.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.103.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.103.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.103.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.104.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.104.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.104.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.105.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.105.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.105.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.106.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.106.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.106.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.107.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.107.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.107.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.108.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.108.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.108.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.108.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.108.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.108.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.109.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.109.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.109.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.109.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.109.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.109.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.11.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.11.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.11.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.110.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.110.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.110.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.110.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.110.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.110.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.111.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.111.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.111.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.111.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.111.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.111.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.112.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.112.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.112.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.112.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.112.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.112.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.113.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.113.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.113.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.113.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.113.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.113.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.114.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.114.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.114.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.114.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.114.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.114.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.115.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.115.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.115.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.115.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.115.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.115.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.116.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.116.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.116.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.116.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.116.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.116.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.117.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.117.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.117.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.117.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.117.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.117.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.118.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.118.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.118.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.118.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.118.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.118.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.119.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.119.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.119.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.119.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.119.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.119.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.12.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.12.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.12.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.120.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.120.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.120.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.120.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.120.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.120.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.121.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.121.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.121.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.121.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.121.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.121.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.122.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.122.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.122.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.122.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.122.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.122.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.123.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.123.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.123.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.123.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.123.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.123.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.124.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.124.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.124.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.124.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.124.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.124.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.125.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.125.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.125.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.125.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.125.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.125.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.126.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.126.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.126.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.126.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.126.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.126.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.127.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.127.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.127.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.127.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.127.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.127.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.13.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.13.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.13.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.14.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.14.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.14.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.15.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.15.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.15.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.16.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.16.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.16.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.17.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.17.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.17.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.18.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.18.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.18.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.19.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.19.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.19.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.2.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.2.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.2.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.20.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.20.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.20.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.21.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.21.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.21.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.22.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.22.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.22.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.23.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.23.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.23.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.24.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.24.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.24.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.25.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.25.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.25.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.26.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.26.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.26.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.27.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.27.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.27.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.28.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.28.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.28.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.29.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.29.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.29.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.3.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.3.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.3.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.30.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.30.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.30.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.31.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.31.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.31.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.32.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.32.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.32.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.32.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.32.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.32.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.33.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.33.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.33.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.33.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.33.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.33.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.34.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.34.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.34.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.34.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.34.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.34.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.35.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.35.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.35.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.35.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.35.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.35.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.36.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.36.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.36.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.36.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.36.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.36.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.37.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.37.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.37.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.37.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.37.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.37.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.38.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.38.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.38.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.38.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.38.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.38.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.39.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.39.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.39.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.39.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.39.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.39.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.4.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.4.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.4.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.40.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.40.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.40.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.40.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.40.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.40.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.41.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.41.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.41.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.41.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.41.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.41.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.42.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.42.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.42.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.42.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.42.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.42.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.43.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.43.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.43.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.43.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.43.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.43.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.44.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.44.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.44.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.44.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.44.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.44.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.45.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.45.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.45.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.45.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.45.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.45.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.46.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.46.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.46.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.46.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.46.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.46.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.47.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.47.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.47.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.47.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.47.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.47.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.48.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.48.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.48.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.48.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.48.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.48.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.49.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.49.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.49.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.49.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.49.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.49.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.5.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.5.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.5.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.50.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.50.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.50.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.50.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.50.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.50.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.51.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.51.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.51.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.51.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.51.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.51.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.52.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.52.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.52.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.52.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.52.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.52.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.53.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.53.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.53.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.53.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.53.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.53.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.54.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.54.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.54.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.54.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.54.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.54.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.55.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.55.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.55.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.55.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.55.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.55.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.56.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.56.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.56.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.56.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.56.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.56.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.57.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.57.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.57.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.57.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.57.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.57.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.58.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.58.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.58.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.58.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.58.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.58.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.59.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.59.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.59.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.59.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.59.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.59.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.6.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.6.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.6.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.60.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.60.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.60.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.60.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.60.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.60.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.61.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.61.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.61.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.61.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.61.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.61.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.62.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.62.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.62.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.62.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.62.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.62.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.63.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.63.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.63.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.63.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.63.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.63.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.64.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.64.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.64.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.64.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.64.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.64.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.65.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.65.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.65.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.65.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.65.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.65.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.66.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.66.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.66.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.66.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.66.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.66.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.67.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.67.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.67.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.67.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.67.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.67.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.68.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.68.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.68.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.68.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.68.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.68.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.69.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.69.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.69.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.69.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.69.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.69.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.7.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.7.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.7.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.70.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.70.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.70.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.70.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.70.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.70.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.71.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.71.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.71.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.71.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.71.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.71.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.72.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.72.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.72.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.72.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.72.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.73.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.73.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.73.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.74.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.74.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.74.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.75.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.75.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.75.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.76.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.76.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.76.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.77.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.77.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.77.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.77.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.78.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.78.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.78.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.78.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.78.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.78.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.79.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.79.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.79.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.79.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.79.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.79.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.8.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.8.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.8.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.80.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.80.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.80.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.80.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.80.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.80.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.81.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.81.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.81.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.81.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.81.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.81.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.82.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.82.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.82.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.82.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.82.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.82.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.83.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.83.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.83.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.83.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.83.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.83.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.84.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.84.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.84.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.84.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.84.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.84.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.85.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.85.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.85.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.85.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.85.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.85.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.86.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.86.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.86.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.86.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.86.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.86.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.87.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.87.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.87.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.87.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.87.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.87.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.88.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.88.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.88.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.88.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.88.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.88.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.89.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.89.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.89.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.89.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.89.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.89.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.9.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.9.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.9.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.90.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.90.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.90.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.90.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.90.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.90.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.91.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.91.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.91.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.91.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.91.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.91.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.92.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.92.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.92.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.92.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.92.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.92.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.93.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.93.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.93.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.93.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.93.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.93.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.94.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.94.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.94.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.94.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.94.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.94.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.95.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.95.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.95.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.95.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.95.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.95.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.96.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.96.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.96.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.96.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.96.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.96.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.97.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.97.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.97.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.97.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.97.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.97.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.98.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.98.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.98.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.98.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.98.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.98.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.99.w1.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.99.w1.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.99.w2.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.99.w2.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.99.w3.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.experts.99.w3.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.shared_experts.down_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.shared_experts.gate_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.shared_experts.up_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.index_k_norm.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.index_k_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.index_k_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.index_q_norm.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.index_q_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.index_q_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.k_norm.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.q_norm.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00009-of-00059.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight_scale": "model-00009-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.e_score_correction_bias": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.gate.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.0.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.0.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.0.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.1.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.1.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.1.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.10.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.10.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.10.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.10.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.10.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.10.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.100.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.100.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.100.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.100.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.100.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.100.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.101.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.101.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.101.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.101.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.101.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.101.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.102.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.102.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.102.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.102.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.102.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.102.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.103.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.103.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.103.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.103.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.103.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.103.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.104.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.104.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.104.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.104.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.104.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.104.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.105.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.105.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.105.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.105.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.105.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.105.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.106.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.106.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.106.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.106.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.106.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.106.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.107.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.107.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.107.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.107.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.107.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.107.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.108.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.108.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.108.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.108.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.108.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.108.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.109.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.109.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.109.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.109.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.109.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.109.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.11.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.11.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.11.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.11.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.11.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.11.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.110.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.110.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.110.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.110.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.110.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.110.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.111.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.111.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.111.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.111.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.111.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.111.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.112.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.112.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.112.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.112.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.112.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.112.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.113.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.113.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.113.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.113.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.113.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.113.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.114.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.114.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.114.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.114.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.114.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.114.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.115.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.115.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.115.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.115.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.115.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.115.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.116.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.116.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.116.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.116.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.116.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.116.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.117.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.117.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.117.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.117.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.117.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.117.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.118.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.118.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.118.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.118.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.118.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.118.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.119.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.119.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.119.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.119.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.119.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.119.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.12.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.12.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.12.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.12.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.12.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.12.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.120.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.120.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.120.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.120.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.120.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.120.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.121.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.121.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.121.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.121.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.121.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.121.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.122.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.122.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.122.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.122.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.122.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.122.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.123.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.123.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.123.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.123.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.123.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.123.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.124.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.124.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.124.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.124.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.124.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.124.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.125.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.125.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.125.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.125.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.125.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.125.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.126.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.126.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.126.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.126.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.126.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.126.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.127.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.127.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.127.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.127.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.127.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.127.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.13.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.13.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.13.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.13.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.13.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.13.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.14.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.14.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.14.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.14.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.14.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.14.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.15.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.15.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.15.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.15.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.15.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.15.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.16.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.16.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.16.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.16.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.16.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.16.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.17.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.17.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.17.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.17.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.17.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.17.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.18.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.18.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.18.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.18.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.18.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.18.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.19.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.19.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.19.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.19.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.19.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.19.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.2.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.2.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.2.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.20.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.20.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.20.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.20.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.20.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.20.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.21.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.21.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.21.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.21.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.21.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.21.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.22.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.22.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.22.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.22.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.22.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.22.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.23.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.23.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.23.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.23.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.23.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.23.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.24.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.24.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.24.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.24.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.24.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.24.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.25.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.25.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.25.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.25.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.25.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.25.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.26.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.26.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.26.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.26.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.26.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.26.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.27.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.27.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.27.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.27.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.27.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.27.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.28.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.28.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.28.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.28.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.28.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.28.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.29.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.29.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.29.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.29.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.29.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.29.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.3.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.3.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.3.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.30.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.30.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.30.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.30.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.30.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.30.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.31.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.31.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.31.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.31.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.31.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.31.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.32.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.32.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.32.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.32.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.32.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.32.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.33.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.33.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.33.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.33.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.33.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.33.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.34.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.34.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.34.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.34.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.34.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.34.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.35.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.35.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.35.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.35.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.35.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.35.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.36.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.36.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.36.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.36.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.36.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.36.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.37.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.37.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.37.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.37.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.37.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.37.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.38.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.38.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.38.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.38.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.38.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.38.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.39.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.39.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.39.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.39.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.39.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.39.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.4.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.4.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.4.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.40.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.40.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.40.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.40.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.40.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.40.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.41.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.41.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.41.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.41.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.41.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.41.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.42.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.42.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.42.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.42.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.42.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.42.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.43.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.43.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.43.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.43.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.43.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.43.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.44.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.44.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.44.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.44.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.44.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.44.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.45.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.45.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.45.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.45.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.45.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.45.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.46.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.46.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.46.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.46.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.46.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.46.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.47.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.47.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.47.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.47.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.47.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.47.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.48.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.48.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.48.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.48.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.48.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.48.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.49.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.49.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.49.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.49.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.49.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.49.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.5.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.5.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.5.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.50.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.50.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.50.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.50.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.50.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.50.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.51.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.51.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.51.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.51.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.51.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.51.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.52.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.52.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.52.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.52.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.52.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.52.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.53.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.53.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.53.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.53.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.53.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.53.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.54.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.54.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.54.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.54.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.54.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.54.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.55.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.55.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.55.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.55.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.55.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.55.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.56.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.56.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.56.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.56.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.56.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.56.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.57.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.57.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.57.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.57.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.57.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.57.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.58.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.58.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.58.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.58.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.58.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.58.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.59.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.59.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.59.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.59.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.59.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.59.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.6.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.6.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.6.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.60.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.60.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.60.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.60.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.60.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.60.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.61.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.61.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.61.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.61.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.61.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.61.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.62.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.62.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.62.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.62.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.62.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.62.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.63.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.63.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.63.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.63.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.63.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.63.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.64.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.64.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.64.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.64.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.64.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.64.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.65.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.65.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.65.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.65.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.65.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.65.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.66.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.66.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.66.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.66.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.66.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.66.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.67.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.67.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.67.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.67.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.67.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.67.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.68.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.68.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.68.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.68.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.68.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.68.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.69.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.69.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.69.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.69.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.69.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.69.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.7.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.7.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.7.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.70.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.70.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.70.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.70.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.70.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.70.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.71.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.71.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.71.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.71.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.71.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.71.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.72.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.72.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.72.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.72.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.72.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.72.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.73.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.73.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.73.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.73.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.73.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.73.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.74.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.74.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.74.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.74.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.74.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.74.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.75.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.75.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.75.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.75.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.75.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.75.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.76.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.76.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.76.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.76.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.76.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.76.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.77.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.77.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.77.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.77.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.77.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.77.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.78.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.78.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.78.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.78.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.78.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.78.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.79.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.79.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.79.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.79.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.79.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.79.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.8.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.8.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.8.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.8.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.8.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.8.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.80.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.80.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.80.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.80.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.80.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.80.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.81.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.81.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.81.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.81.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.81.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.81.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.82.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.82.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.82.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.82.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.82.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.82.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.83.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.83.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.83.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.83.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.83.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.83.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.84.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.84.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.84.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.84.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.84.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.84.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.85.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.85.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.85.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.85.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.85.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.85.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.86.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.86.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.86.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.86.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.86.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.86.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.87.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.87.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.87.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.87.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.87.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.87.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.88.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.88.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.88.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.88.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.88.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.88.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.89.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.89.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.89.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.89.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.89.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.89.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.9.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.9.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.9.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.9.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.9.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.9.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.90.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.90.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.90.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.90.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.90.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.90.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.91.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.91.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.91.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.91.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.91.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.91.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.92.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.92.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.92.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.92.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.92.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.92.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.93.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.93.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.93.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.93.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.93.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.93.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.94.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.94.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.94.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.94.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.94.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.94.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.95.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.95.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.95.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.95.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.95.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.95.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.96.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.96.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.96.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.96.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.96.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.96.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.97.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.97.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.97.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.97.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.97.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.97.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.98.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.98.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.98.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.98.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.98.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.98.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.99.w1.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.99.w1.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.99.w2.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.99.w2.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.99.w3.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.experts.99.w3.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.shared_experts.down_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.shared_experts.gate_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.shared_experts.up_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.index_k_norm.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.index_k_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.index_k_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.index_q_norm.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.index_q_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.index_q_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.k_norm.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.q_norm.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00027-of-00059.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight_scale": "model-00027-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.gate.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.108.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.108.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.108.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.108.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.108.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.108.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.109.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.109.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.109.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.109.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.109.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.109.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.11.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.11.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.11.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.11.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.11.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.11.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.110.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.110.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.110.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.110.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.110.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.110.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.111.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.111.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.111.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.111.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.111.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.111.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.112.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.112.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.112.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.112.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.112.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.112.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.113.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.113.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.113.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.113.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.113.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.113.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.114.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.114.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.114.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.114.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.114.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.114.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.115.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.115.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.115.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.115.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.115.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.115.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.116.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.116.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.116.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.116.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.116.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.116.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.117.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.117.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.117.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.117.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.117.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.117.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.118.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.118.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.118.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.118.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.118.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.118.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.119.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.119.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.119.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.119.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.119.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.119.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.12.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.12.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.12.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.12.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.12.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.12.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.120.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.120.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.120.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.120.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.120.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.120.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.121.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.121.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.121.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.121.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.121.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.121.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.122.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.122.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.122.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.122.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.122.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.122.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.123.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.123.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.123.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.123.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.123.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.123.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.124.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.124.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.124.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.124.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.124.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.124.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.125.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.125.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.125.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.125.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.125.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.125.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.126.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.126.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.126.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.126.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.126.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.126.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.127.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.127.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.127.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.127.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.127.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.127.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.13.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.13.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.13.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.13.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.13.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.13.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.14.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.14.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.14.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.14.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.14.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.14.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.15.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.15.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.15.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.15.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.15.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.15.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.16.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.16.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.16.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.16.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.16.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.16.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.17.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.17.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.17.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.17.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.17.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.17.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.18.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.18.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.18.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.18.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.18.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.18.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.19.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.19.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.19.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.19.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.19.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.19.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.2.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.2.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.2.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.20.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.20.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.20.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.20.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.20.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.20.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.21.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.21.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.21.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.21.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.21.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.21.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.22.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.22.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.22.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.22.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.22.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.22.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.23.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.23.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.23.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.23.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.23.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.23.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.24.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.24.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.24.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.24.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.24.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.24.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.25.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.25.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.25.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.25.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.25.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.25.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.26.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.26.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.26.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.26.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.26.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.26.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.27.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.27.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.27.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.27.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.27.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.27.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.28.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.28.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.28.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.28.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.28.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.28.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.29.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.29.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.29.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.29.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.29.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.29.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.3.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.3.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.3.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.30.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.30.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.30.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.30.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.30.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.30.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.31.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.31.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.31.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.31.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.31.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.31.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.32.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.32.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.32.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.32.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.32.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.32.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.33.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.33.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.33.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.33.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.33.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.33.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.34.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.34.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.34.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.34.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.34.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.34.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.35.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.35.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.35.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.35.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.35.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.35.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.36.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.36.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.36.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.36.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.36.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.36.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.37.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.37.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.37.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.37.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.37.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.37.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.38.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.38.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.38.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.38.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.38.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.38.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.39.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.39.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.39.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.39.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.39.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.39.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.4.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.4.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.4.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.40.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.40.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.40.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.40.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.40.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.40.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.41.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.41.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.41.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.41.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.41.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.41.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.42.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.42.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.42.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.42.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.42.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.42.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.43.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.43.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.43.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.43.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.43.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.43.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.44.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.44.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.44.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.44.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.44.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.44.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.45.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.45.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.45.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.45.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.45.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.45.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.46.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.46.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.46.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.46.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.46.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.46.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.47.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.47.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.47.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.47.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.47.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.47.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.48.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.48.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.48.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.48.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.48.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.48.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.49.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.49.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.49.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.49.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.49.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.49.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.5.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.5.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.5.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.50.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.50.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.50.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.50.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.50.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.50.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.51.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.51.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.51.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.51.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.51.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.51.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.52.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.52.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.52.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.52.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.52.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.52.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.53.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.53.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.53.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.53.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.53.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.53.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.54.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.54.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.54.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.54.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.54.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.54.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.55.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.55.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.55.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.55.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.55.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.55.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.56.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.56.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.56.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.56.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.56.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.56.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.57.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.57.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.57.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.57.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.57.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.57.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.58.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.58.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.58.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.58.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.58.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.58.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.59.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.59.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.59.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.59.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.59.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.59.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.6.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.6.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.6.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.60.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.60.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.60.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.60.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.60.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.60.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.61.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.61.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.61.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.61.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.61.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.61.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.62.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.62.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.62.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.62.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.62.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.62.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.63.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.63.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.63.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.63.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.63.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.63.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.64.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.64.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.64.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.64.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.64.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.64.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.65.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.65.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.65.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.65.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.65.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.65.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.66.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.66.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.66.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.66.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.66.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.66.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.67.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.67.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.67.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.67.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.67.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.67.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.68.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.68.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.68.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.68.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.68.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.68.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.69.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.69.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.69.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.69.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.69.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.69.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.7.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.7.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.7.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.70.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.70.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.70.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.70.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.70.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.70.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.71.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.71.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.71.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.71.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.71.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.71.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.72.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.72.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.72.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.72.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.72.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.72.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.73.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.73.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.73.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.73.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.73.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.73.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.74.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.74.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.74.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.74.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.74.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.74.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.75.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.75.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.75.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.75.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.75.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.75.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.76.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.76.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.76.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.76.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.76.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.76.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.77.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.77.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.77.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.77.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.77.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.77.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.78.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.78.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.78.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.78.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.78.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.78.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.79.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.79.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.79.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.79.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.79.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.79.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.8.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.8.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.8.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.8.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.8.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.8.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.80.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.80.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.80.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.80.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.80.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.80.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.81.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.81.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.81.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.81.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.81.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.81.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.82.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.82.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.82.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.82.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.82.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.82.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.83.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.83.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.83.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.83.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.83.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.83.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.84.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.84.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.84.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.84.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.84.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.84.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.85.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.85.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.85.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.85.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.85.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.85.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.86.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.86.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.86.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.86.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.86.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.86.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.87.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.87.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.87.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.87.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.87.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.87.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.88.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.88.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.88.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.88.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.88.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.88.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.89.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.89.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.89.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.89.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.89.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.89.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.9.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.9.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.9.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.9.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.9.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.9.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.90.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.90.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.90.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.90.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.90.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.90.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.91.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.91.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.91.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.91.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.91.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.91.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.92.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.92.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.92.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.92.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.92.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.92.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.93.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.93.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.93.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.93.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.93.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.93.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.94.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.94.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.94.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.94.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.94.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.94.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.95.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.95.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.95.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.95.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.95.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.95.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.96.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.96.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.96.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.96.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.96.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.96.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.97.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.97.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.97.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.97.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.97.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.97.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.98.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.98.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.98.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.98.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.98.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.98.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.99.w1.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.99.w1.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.99.w2.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.99.w2.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.99.w3.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.experts.99.w3.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.shared_experts.down_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.shared_experts.gate_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.shared_experts.up_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.input_layernorm.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.post_attention_layernorm.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.index_k_norm.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.index_k_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.index_k_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.index_q_norm.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.index_q_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.index_q_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.k_norm.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.k_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.k_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.o_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.o_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.q_norm.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.q_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.q_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.v_proj.weight": "model-00037-of-00059.safetensors", + "language_model.model.layers.37.self_attn.v_proj.weight_scale": "model-00037-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.e_score_correction_bias": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.gate.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.0.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.0.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.0.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.1.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.1.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.1.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.10.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.10.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.10.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.10.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.10.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.10.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.100.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.100.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.100.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.100.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.100.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.100.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.101.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.101.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.101.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.101.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.101.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.101.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.102.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.102.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.102.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.102.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.102.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.102.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.103.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.103.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.103.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.103.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.103.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.103.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.104.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.104.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.104.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.104.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.104.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.104.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.105.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.105.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.105.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.105.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.105.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.105.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.106.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.106.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.106.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.106.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.106.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.106.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.107.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.107.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.107.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.107.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.107.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.107.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.108.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.108.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.108.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.108.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.108.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.108.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.109.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.109.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.109.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.109.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.109.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.109.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.11.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.11.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.11.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.11.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.11.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.11.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.110.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.110.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.110.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.110.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.110.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.110.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.111.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.111.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.111.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.111.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.111.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.111.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.112.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.112.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.112.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.112.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.112.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.112.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.113.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.113.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.113.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.113.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.113.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.113.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.114.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.114.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.114.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.114.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.114.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.114.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.115.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.115.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.115.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.115.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.115.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.115.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.116.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.116.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.116.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.116.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.116.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.116.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.117.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.117.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.117.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.117.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.117.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.117.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.118.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.118.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.118.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.118.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.118.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.118.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.119.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.119.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.119.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.119.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.119.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.119.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.12.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.12.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.12.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.12.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.12.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.12.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.120.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.120.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.120.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.120.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.120.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.120.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.121.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.121.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.121.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.121.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.121.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.121.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.122.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.122.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.122.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.122.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.122.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.122.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.123.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.123.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.123.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.123.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.123.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.123.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.124.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.124.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.124.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.124.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.124.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.124.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.125.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.125.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.125.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.125.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.125.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.125.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.126.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.126.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.126.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.126.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.126.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.126.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.127.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.127.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.127.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.127.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.127.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.127.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.13.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.13.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.13.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.13.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.13.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.13.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.14.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.14.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.14.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.14.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.14.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.14.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.15.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.15.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.15.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.15.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.15.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.15.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.16.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.16.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.16.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.16.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.16.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.16.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.17.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.17.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.17.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.17.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.17.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.17.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.18.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.18.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.18.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.18.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.18.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.18.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.19.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.19.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.19.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.19.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.19.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.19.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.2.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.2.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.2.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.20.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.20.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.20.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.20.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.20.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.20.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.21.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.21.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.21.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.21.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.21.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.21.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.22.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.22.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.22.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.22.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.22.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.22.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.23.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.23.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.23.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.23.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.23.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.23.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.24.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.24.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.24.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.24.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.24.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.24.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.25.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.25.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.25.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.25.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.25.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.25.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.26.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.26.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.26.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.26.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.26.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.26.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.27.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.27.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.27.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.27.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.27.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.27.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.28.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.28.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.28.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.28.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.28.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.28.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.29.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.29.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.29.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.29.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.29.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.29.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.3.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.3.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.3.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.30.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.30.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.30.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.30.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.30.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.30.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.31.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.31.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.31.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.31.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.31.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.31.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.32.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.32.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.32.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.32.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.32.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.32.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.33.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.33.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.33.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.33.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.33.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.33.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.34.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.34.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.34.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.34.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.34.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.34.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.35.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.35.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.35.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.35.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.35.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.35.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.36.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.36.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.36.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.36.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.36.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.36.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.37.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.37.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.37.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.37.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.37.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.37.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.38.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.38.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.38.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.38.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.38.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.38.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.39.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.39.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.39.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.39.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.39.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.39.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.4.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.4.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.4.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.40.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.40.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.40.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.40.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.40.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.40.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.41.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.41.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.41.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.41.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.41.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.41.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.42.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.42.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.42.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.42.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.42.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.42.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.43.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.43.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.43.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.43.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.43.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.43.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.44.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.44.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.44.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.44.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.44.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.44.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.45.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.45.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.45.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.45.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.45.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.45.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.46.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.46.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.46.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.46.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.46.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.46.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.47.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.47.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.47.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.47.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.47.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.47.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.48.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.48.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.48.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.48.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.48.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.48.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.49.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.49.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.49.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.49.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.49.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.49.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.5.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.5.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.5.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.50.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.50.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.50.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.50.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.50.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.50.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.51.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.51.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.51.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.51.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.51.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.51.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.52.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.52.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.52.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.52.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.52.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.52.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.53.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.53.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.53.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.53.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.53.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.53.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.54.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.54.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.54.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.54.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.54.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.54.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.55.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.55.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.55.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.55.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.55.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.55.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.56.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.56.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.56.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.56.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.56.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.56.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.57.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.57.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.57.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.57.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.57.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.57.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.58.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.58.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.58.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.58.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.58.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.58.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.59.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.59.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.59.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.59.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.59.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.59.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.6.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.6.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.6.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.60.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.60.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.60.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.60.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.60.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.60.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.61.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.61.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.61.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.61.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.61.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.61.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.62.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.62.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.62.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.62.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.62.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.62.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.63.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.63.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.63.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.63.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.63.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.63.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.64.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.64.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.64.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.64.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.64.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.64.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.65.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.65.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.65.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.65.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.65.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.65.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.66.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.66.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.66.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.66.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.66.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.66.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.67.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.67.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.67.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.67.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.67.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.67.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.68.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.68.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.68.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.68.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.68.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.68.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.69.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.69.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.69.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.69.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.69.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.69.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.7.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.7.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.7.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.70.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.70.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.70.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.70.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.70.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.70.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.71.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.71.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.71.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.71.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.71.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.71.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.72.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.72.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.72.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.72.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.72.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.72.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.73.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.73.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.73.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.73.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.73.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.73.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.74.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.74.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.74.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.74.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.74.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.74.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.75.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.75.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.75.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.75.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.75.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.75.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.76.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.76.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.76.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.76.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.76.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.76.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.77.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.77.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.77.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.77.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.77.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.77.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.78.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.78.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.78.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.78.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.78.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.78.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.79.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.79.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.79.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.79.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.79.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.79.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.8.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.8.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.8.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.8.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.8.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.8.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.80.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.80.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.80.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.80.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.80.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.80.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.81.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.81.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.81.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.81.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.81.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.81.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.82.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.82.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.82.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.82.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.82.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.82.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.83.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.83.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.83.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.83.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.83.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.83.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.84.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.84.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.84.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.84.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.84.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.84.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.85.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.85.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.85.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.85.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.85.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.85.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.86.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.86.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.86.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.86.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.86.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.86.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.87.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.87.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.87.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.87.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.87.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.87.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.88.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.88.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.88.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.88.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.88.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.88.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.89.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.89.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.89.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.89.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.89.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.89.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.9.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.9.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.9.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.9.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.9.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.9.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.90.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.90.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.90.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.90.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.90.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.90.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.91.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.91.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.91.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.91.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.91.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.91.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.92.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.92.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.92.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.92.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.92.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.92.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.93.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.93.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.93.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.93.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.93.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.93.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.94.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.94.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.94.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.94.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.94.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.94.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.95.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.95.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.95.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.95.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.95.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.95.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.96.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.96.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.96.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.96.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.96.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.96.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.97.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.97.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.97.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.97.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.97.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.97.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.98.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.98.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.98.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.98.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.98.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.98.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.99.w1.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.99.w1.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.99.w2.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.99.w2.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.99.w3.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.experts.99.w3.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.shared_experts.down_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.shared_experts.gate_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.shared_experts.up_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.input_layernorm.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.post_attention_layernorm.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.index_k_norm.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.index_k_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.index_k_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.index_q_norm.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.index_q_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.index_q_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.k_norm.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.k_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.k_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.o_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.o_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.q_norm.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.q_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.q_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.v_proj.weight": "model-00033-of-00059.safetensors", + "language_model.model.layers.33.self_attn.v_proj.weight_scale": "model-00033-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.gate.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.108.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.108.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.108.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.108.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.108.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.108.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.109.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.109.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.109.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.109.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.109.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.109.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.11.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.11.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.11.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.11.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.11.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.11.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.110.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.110.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.110.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.110.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.110.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.110.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.111.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.111.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.111.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.111.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.111.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.111.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.112.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.112.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.112.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.112.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.112.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.112.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.113.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.113.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.113.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.113.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.113.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.113.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.114.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.114.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.114.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.114.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.114.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.114.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.115.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.115.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.115.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.115.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.115.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.115.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.116.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.116.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.116.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.116.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.116.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.116.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.117.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.117.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.117.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.117.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.117.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.117.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.118.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.118.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.118.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.118.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.118.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.118.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.119.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.119.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.119.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.119.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.119.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.119.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.12.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.12.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.12.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.12.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.12.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.12.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.120.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.120.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.120.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.120.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.120.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.120.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.121.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.121.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.121.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.121.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.121.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.121.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.122.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.122.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.122.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.122.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.122.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.122.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.123.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.123.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.123.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.123.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.123.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.123.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.124.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.124.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.124.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.124.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.124.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.124.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.125.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.125.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.125.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.125.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.125.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.125.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.126.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.126.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.126.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.126.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.126.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.126.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.127.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.127.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.127.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.127.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.127.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.127.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.13.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.13.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.13.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.13.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.13.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.13.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.14.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.14.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.14.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.14.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.14.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.14.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.15.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.15.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.15.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.15.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.15.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.15.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.16.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.16.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.16.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.16.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.16.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.16.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.17.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.17.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.17.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.17.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.17.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.17.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.18.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.18.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.18.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.18.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.18.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.18.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.19.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.19.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.19.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.19.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.19.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.19.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.2.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.2.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.2.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.20.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.20.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.20.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.20.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.20.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.20.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.21.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.21.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.21.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.21.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.21.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.21.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.22.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.22.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.22.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.22.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.22.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.22.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.23.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.23.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.23.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.23.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.23.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.23.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.24.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.24.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.24.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.24.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.24.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.24.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.25.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.25.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.25.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.25.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.25.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.25.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.26.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.26.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.26.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.26.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.26.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.26.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.27.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.27.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.27.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.27.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.27.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.27.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.28.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.28.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.28.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.28.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.28.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.28.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.29.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.29.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.29.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.29.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.29.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.29.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.3.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.3.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.3.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.3.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.3.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.3.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.30.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.30.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.30.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.30.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.30.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.30.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.31.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.31.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.31.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.31.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.31.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.31.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.32.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.32.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.32.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.32.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.32.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.32.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.33.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.33.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.33.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.33.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.33.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.33.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.34.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.34.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.34.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.34.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.34.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.34.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.35.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.35.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.35.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.35.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.35.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.35.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.36.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.36.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.36.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.36.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.36.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.36.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.37.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.37.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.37.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.37.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.37.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.37.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.38.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.38.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.38.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.38.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.38.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.38.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.39.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.39.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.39.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.39.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.39.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.39.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.4.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.4.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.4.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.4.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.4.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.4.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.40.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.40.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.40.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.40.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.40.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.40.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.41.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.41.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.41.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.41.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.41.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.41.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.42.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.42.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.42.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.42.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.42.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.42.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.43.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.43.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.43.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.43.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.43.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.43.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.44.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.44.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.44.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.44.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.44.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.44.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.45.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.45.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.45.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.45.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.45.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.45.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.46.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.46.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.46.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.46.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.46.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.46.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.47.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.47.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.47.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.47.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.47.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.47.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.48.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.48.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.48.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.48.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.48.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.48.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.49.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.49.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.49.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.49.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.49.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.49.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.5.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.5.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.5.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.5.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.5.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.5.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.50.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.50.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.50.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.50.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.50.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.50.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.51.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.51.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.51.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.51.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.51.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.51.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.52.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.52.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.52.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.52.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.52.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.52.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.53.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.53.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.53.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.53.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.53.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.53.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.54.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.54.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.54.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.54.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.54.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.54.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.55.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.55.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.55.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.55.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.55.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.55.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.56.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.56.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.56.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.56.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.56.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.56.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.57.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.57.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.57.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.57.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.57.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.57.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.58.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.58.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.58.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.58.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.58.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.58.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.59.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.59.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.59.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.59.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.59.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.59.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.6.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.6.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.6.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.6.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.6.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.6.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.60.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.60.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.60.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.60.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.60.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.60.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.61.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.61.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.61.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.61.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.61.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.61.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.62.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.62.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.62.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.62.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.62.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.62.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.63.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.63.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.63.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.63.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.63.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.63.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.64.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.64.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.64.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.64.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.64.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.64.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.65.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.65.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.65.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.65.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.65.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.65.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.66.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.66.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.66.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.66.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.66.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.66.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.67.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.67.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.67.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.67.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.67.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.67.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.68.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.68.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.68.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.68.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.68.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.68.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.69.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.69.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.69.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.69.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.69.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.69.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.7.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.7.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.7.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.7.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.7.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.7.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.70.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.70.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.70.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.70.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.70.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.70.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.71.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.71.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.71.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.71.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.71.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.71.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.72.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.72.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.72.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.72.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.72.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.72.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.73.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.73.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.73.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.73.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.73.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.73.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.74.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.74.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.74.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.74.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.74.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.74.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.75.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.75.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.75.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.75.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.75.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.75.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.76.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.76.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.76.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.76.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.76.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.76.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.77.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.77.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.77.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.77.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.77.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.77.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.78.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.78.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.78.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.78.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.78.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.78.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.79.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.79.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.79.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.79.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.79.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.79.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.8.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.8.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.8.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.8.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.8.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.8.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.80.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.80.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.80.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.80.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.80.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.80.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.81.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.81.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.81.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.81.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.81.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.81.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.82.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.82.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.82.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.82.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.82.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.82.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.83.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.83.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.83.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.83.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.83.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.83.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.84.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.84.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.84.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.84.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.84.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.84.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.85.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.85.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.85.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.85.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.85.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.85.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.86.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.86.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.86.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.86.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.86.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.86.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.87.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.87.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.87.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.87.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.87.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.87.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.88.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.88.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.88.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.88.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.88.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.88.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.89.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.89.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.89.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.89.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.89.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.89.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.9.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.9.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.9.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.9.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.9.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.9.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.90.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.90.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.90.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.90.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.90.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.90.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.91.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.91.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.91.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.91.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.91.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.91.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.92.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.92.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.92.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.92.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.92.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.92.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.93.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.93.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.93.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.93.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.93.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.93.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.94.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.94.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.94.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.94.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.94.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.94.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.95.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.95.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.95.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.95.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.95.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.95.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.96.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.96.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.96.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.96.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.96.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.96.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.97.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.97.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.97.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.97.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.97.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.97.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.98.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.98.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.98.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.98.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.98.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.98.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.99.w1.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.99.w1.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.99.w2.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.99.w2.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.99.w3.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.99.w3.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.shared_experts.down_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.shared_experts.gate_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.shared_experts.up_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.input_layernorm.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.post_attention_layernorm.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.index_k_norm.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.index_k_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.index_k_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.index_q_norm.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.index_q_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.index_q_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.k_norm.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.k_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.k_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.o_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.o_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.q_norm.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.q_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.q_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.v_proj.weight": "model-00052-of-00059.safetensors", + "language_model.model.layers.52.self_attn.v_proj.weight_scale": "model-00052-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.gate.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.108.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.108.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.108.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.108.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.108.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.108.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.109.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.109.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.109.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.109.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.109.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.109.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.11.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.11.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.11.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.11.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.11.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.11.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.110.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.110.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.110.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.110.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.110.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.110.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.111.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.111.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.111.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.111.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.111.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.111.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.112.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.112.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.112.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.112.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.112.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.112.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.113.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.113.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.113.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.113.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.113.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.113.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.114.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.114.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.114.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.114.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.114.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.114.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.115.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.115.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.115.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.115.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.115.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.115.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.116.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.116.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.116.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.116.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.116.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.116.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.117.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.117.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.117.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.117.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.117.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.117.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.118.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.118.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.118.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.118.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.118.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.118.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.119.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.119.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.119.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.119.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.119.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.119.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.12.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.12.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.12.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.12.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.12.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.12.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.120.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.120.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.120.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.120.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.120.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.120.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.121.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.121.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.121.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.121.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.121.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.121.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.122.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.122.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.122.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.122.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.122.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.122.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.123.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.123.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.123.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.123.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.123.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.123.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.124.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.124.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.124.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.124.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.124.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.124.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.125.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.125.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.125.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.125.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.125.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.125.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.126.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.126.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.126.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.126.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.126.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.126.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.127.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.127.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.127.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.127.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.127.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.127.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.13.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.13.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.13.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.13.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.13.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.13.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.14.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.14.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.14.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.14.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.14.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.14.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.15.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.15.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.15.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.15.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.15.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.15.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.16.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.16.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.16.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.16.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.16.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.16.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.17.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.17.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.17.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.17.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.17.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.17.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.18.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.18.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.18.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.18.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.18.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.18.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.19.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.19.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.19.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.19.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.19.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.19.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.2.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.2.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.2.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.20.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.20.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.20.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.20.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.20.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.20.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.21.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.21.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.21.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.21.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.21.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.21.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.22.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.22.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.22.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.22.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.22.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.22.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.23.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.23.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.23.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.23.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.23.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.23.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.24.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.24.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.24.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.24.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.24.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.24.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.25.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.25.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.25.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.25.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.25.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.25.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.26.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.26.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.26.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.26.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.26.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.26.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.27.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.27.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.27.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.27.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.27.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.27.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.28.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.28.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.28.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.28.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.28.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.28.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.29.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.29.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.29.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.29.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.29.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.29.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.3.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.3.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.3.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.3.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.3.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.3.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.30.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.30.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.30.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.30.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.30.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.30.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.31.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.31.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.31.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.31.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.31.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.31.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.32.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.32.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.32.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.32.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.32.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.32.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.33.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.33.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.33.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.33.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.33.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.33.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.34.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.34.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.34.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.34.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.34.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.34.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.35.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.35.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.35.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.35.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.35.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.35.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.36.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.36.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.36.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.36.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.36.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.36.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.37.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.37.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.37.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.37.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.37.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.37.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.38.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.38.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.38.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.38.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.38.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.38.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.39.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.39.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.39.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.39.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.39.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.39.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.4.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.4.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.4.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.4.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.4.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.4.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.40.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.40.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.40.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.40.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.40.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.40.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.41.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.41.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.41.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.41.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.41.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.41.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.42.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.42.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.42.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.42.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.42.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.42.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.43.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.43.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.43.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.43.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.43.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.43.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.44.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.44.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.44.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.44.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.44.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.44.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.45.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.45.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.45.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.45.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.45.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.45.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.46.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.46.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.46.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.46.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.46.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.46.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.47.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.47.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.47.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.47.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.47.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.47.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.48.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.48.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.48.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.48.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.48.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.48.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.49.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.49.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.49.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.49.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.49.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.49.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.5.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.5.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.5.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.5.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.5.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.5.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.50.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.50.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.50.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.50.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.50.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.50.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.51.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.51.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.51.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.51.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.51.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.51.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.52.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.52.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.52.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.52.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.52.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.52.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.53.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.53.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.53.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.53.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.53.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.53.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.54.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.54.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.54.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.54.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.54.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.54.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.55.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.55.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.55.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.55.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.55.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.55.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.56.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.56.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.56.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.56.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.56.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.56.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.57.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.57.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.57.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.57.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.57.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.57.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.58.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.58.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.58.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.58.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.58.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.58.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.59.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.59.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.59.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.59.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.59.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.59.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.6.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.6.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.6.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.6.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.6.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.6.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.60.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.60.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.60.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.60.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.60.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.60.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.61.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.61.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.61.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.61.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.61.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.61.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.62.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.62.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.62.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.62.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.62.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.62.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.63.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.63.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.63.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.63.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.63.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.63.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.64.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.64.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.64.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.64.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.64.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.64.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.65.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.65.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.65.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.65.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.65.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.65.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.66.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.66.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.66.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.66.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.66.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.66.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.67.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.67.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.67.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.67.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.67.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.67.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.68.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.68.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.68.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.68.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.68.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.68.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.69.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.69.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.69.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.69.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.69.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.69.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.7.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.7.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.7.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.7.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.7.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.7.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.70.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.70.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.70.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.70.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.70.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.70.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.71.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.71.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.71.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.71.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.71.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.71.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.72.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.72.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.72.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.72.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.72.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.72.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.73.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.73.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.73.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.73.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.73.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.73.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.74.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.74.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.74.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.74.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.74.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.74.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.75.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.75.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.75.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.75.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.75.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.75.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.76.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.76.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.76.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.76.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.76.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.76.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.77.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.77.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.77.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.77.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.77.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.77.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.78.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.78.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.78.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.78.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.78.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.78.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.79.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.79.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.79.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.79.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.79.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.79.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.8.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.8.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.8.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.8.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.8.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.8.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.80.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.80.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.80.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.80.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.80.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.80.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.81.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.81.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.81.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.81.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.81.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.81.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.82.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.82.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.82.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.82.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.82.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.82.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.83.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.83.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.83.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.83.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.83.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.83.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.84.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.84.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.84.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.84.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.84.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.84.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.85.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.85.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.85.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.85.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.85.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.85.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.86.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.86.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.86.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.86.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.86.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.86.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.87.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.87.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.87.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.87.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.87.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.87.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.88.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.88.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.88.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.88.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.88.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.88.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.89.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.89.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.89.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.89.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.89.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.89.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.9.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.9.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.9.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.9.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.9.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.9.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.90.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.90.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.90.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.90.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.90.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.90.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.91.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.91.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.91.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.91.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.91.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.91.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.92.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.92.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.92.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.92.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.92.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.92.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.93.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.93.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.93.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.93.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.93.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.93.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.94.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.94.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.94.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.94.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.94.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.94.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.95.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.95.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.95.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.95.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.95.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.95.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.96.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.96.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.96.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.96.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.96.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.96.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.97.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.97.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.97.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.97.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.97.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.97.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.98.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.98.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.98.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.98.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.98.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.98.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.99.w1.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.99.w1.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.99.w2.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.99.w2.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.99.w3.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.experts.99.w3.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.shared_experts.down_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.shared_experts.gate_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.shared_experts.up_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.input_layernorm.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.post_attention_layernorm.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.index_k_norm.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.index_k_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.index_k_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.index_q_norm.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.index_q_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.index_q_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.k_norm.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.k_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.k_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.o_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.o_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.q_norm.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.q_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.q_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.v_proj.weight": "model-00051-of-00059.safetensors", + "language_model.model.layers.51.self_attn.v_proj.weight_scale": "model-00051-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.e_score_correction_bias": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.e_score_correction_bias": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.0.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.0.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.0.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.1.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.1.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.1.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.10.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.10.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.10.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.100.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.100.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.100.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.101.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.101.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.101.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.102.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.102.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.102.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.103.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.103.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.103.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.104.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.104.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.104.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.105.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.105.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.105.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.106.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.106.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.106.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.107.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.107.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.107.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.108.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.108.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.108.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.108.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.108.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.108.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.109.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.109.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.109.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.109.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.109.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.109.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.11.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.11.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.11.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.110.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.110.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.110.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.110.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.110.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.110.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.111.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.111.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.111.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.111.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.111.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.111.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.112.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.112.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.112.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.112.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.112.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.112.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.113.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.113.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.113.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.113.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.113.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.113.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.114.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.114.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.114.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.114.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.114.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.114.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.115.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.115.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.115.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.115.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.115.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.115.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.116.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.116.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.116.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.116.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.116.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.116.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.117.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.117.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.117.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.117.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.117.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.117.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.118.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.118.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.118.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.118.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.118.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.118.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.119.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.119.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.119.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.119.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.119.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.119.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.12.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.12.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.12.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.120.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.120.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.120.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.120.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.120.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.120.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.121.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.121.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.121.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.121.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.121.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.121.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.122.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.122.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.122.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.122.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.122.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.122.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.123.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.123.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.123.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.123.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.123.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.123.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.124.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.124.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.124.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.124.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.124.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.124.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.125.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.125.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.125.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.125.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.125.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.125.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.126.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.126.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.126.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.126.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.126.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.126.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.127.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.127.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.127.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.127.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.127.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.127.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.13.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.13.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.13.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.14.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.14.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.14.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.15.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.15.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.15.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.16.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.16.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.16.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.17.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.17.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.17.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.18.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.18.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.18.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.19.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.19.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.19.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.2.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.2.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.2.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.20.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.20.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.20.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.21.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.21.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.21.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.22.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.22.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.22.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.23.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.23.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.23.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.24.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.24.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.24.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.25.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.25.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.25.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.26.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.26.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.26.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.27.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.27.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.27.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.28.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.28.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.28.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.29.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.29.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.29.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.3.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.3.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.3.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.30.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.30.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.30.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.31.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.31.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.31.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.32.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.32.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.32.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.32.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.32.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.32.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.33.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.33.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.33.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.33.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.33.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.33.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.34.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.34.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.34.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.34.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.34.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.34.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.35.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.35.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.35.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.35.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.35.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.35.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.36.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.36.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.36.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.36.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.36.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.36.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.37.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.37.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.37.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.37.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.37.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.37.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.38.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.38.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.38.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.38.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.38.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.38.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.39.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.39.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.39.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.39.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.39.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.39.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.4.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.4.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.4.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.40.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.40.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.40.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.40.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.40.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.40.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.41.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.41.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.41.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.41.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.41.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.41.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.42.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.42.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.42.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.42.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.42.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.42.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.43.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.43.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.43.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.43.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.43.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.43.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.44.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.44.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.44.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.44.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.44.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.44.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.45.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.45.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.45.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.45.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.45.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.45.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.46.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.46.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.46.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.46.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.46.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.46.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.47.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.47.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.47.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.47.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.47.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.47.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.48.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.48.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.48.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.48.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.48.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.48.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.49.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.49.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.49.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.49.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.49.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.49.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.5.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.5.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.5.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.50.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.50.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.50.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.50.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.50.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.50.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.51.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.51.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.51.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.51.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.51.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.51.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.52.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.52.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.52.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.52.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.52.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.52.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.53.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.53.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.53.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.53.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.53.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.53.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.54.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.54.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.54.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.54.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.54.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.54.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.55.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.55.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.55.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.55.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.55.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.55.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.56.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.56.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.56.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.56.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.56.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.56.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.57.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.57.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.57.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.57.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.57.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.57.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.58.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.58.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.58.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.58.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.58.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.58.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.59.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.59.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.59.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.59.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.59.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.59.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.6.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.6.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.6.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.60.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.60.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.60.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.60.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.60.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.60.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.61.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.61.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.61.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.61.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.61.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.61.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.62.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.62.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.62.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.62.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.62.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.62.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.63.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.63.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.63.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.63.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.63.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.63.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.64.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.64.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.64.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.64.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.64.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.64.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.65.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.65.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.65.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.65.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.65.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.65.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.66.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.66.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.66.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.66.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.66.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.66.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.67.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.67.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.67.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.67.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.67.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.67.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.68.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.68.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.68.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.68.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.68.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.68.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.69.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.69.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.69.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.69.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.69.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.69.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.7.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.7.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.7.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.70.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.70.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.70.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.70.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.70.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.70.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.71.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.71.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.71.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.71.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.71.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.71.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.72.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.72.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.72.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.72.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.72.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.72.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.73.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.73.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.73.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.73.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.73.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.73.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.74.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.74.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.74.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.74.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.74.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.74.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.75.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.75.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.75.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.75.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.75.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.75.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.76.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.76.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.76.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.76.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.76.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.76.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.77.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.77.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.77.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.77.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.77.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.77.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.78.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.78.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.78.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.78.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.78.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.78.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.79.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.79.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.79.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.79.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.79.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.79.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.8.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.8.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.8.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.80.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.80.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.80.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.80.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.80.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.80.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.81.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.81.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.81.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.81.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.81.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.81.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.82.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.82.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.82.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.82.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.82.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.82.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.83.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.83.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.83.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.83.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.83.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.83.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.84.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.84.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.84.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.84.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.84.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.84.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.85.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.85.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.85.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.85.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.85.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.85.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.86.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.86.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.86.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.86.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.86.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.86.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.87.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.87.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.87.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.87.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.87.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.87.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.88.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.88.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.88.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.88.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.88.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.88.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.89.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.89.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.89.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.89.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.89.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.89.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.9.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.9.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.9.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.90.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.90.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.90.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.90.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.90.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.90.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.91.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.91.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.91.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.91.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.91.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.91.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.92.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.92.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.92.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.92.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.92.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.92.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.93.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.93.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.93.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.93.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.93.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.93.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.94.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.94.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.94.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.94.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.94.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.94.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.95.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.95.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.95.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.95.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.95.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.95.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.96.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.96.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.96.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.96.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.96.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.96.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.97.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.97.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.97.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.97.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.97.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.97.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.98.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.98.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.98.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.98.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.98.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.98.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.99.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.99.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.99.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.99.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.99.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.experts.99.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.shared_experts.down_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.shared_experts.gate_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.shared_experts.up_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.index_k_norm.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.index_k_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.index_k_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.index_q_norm.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.index_q_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.index_q_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.k_norm.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.q_norm.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.0.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.0.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.0.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.1.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.1.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.1.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.10.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.10.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.10.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.100.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.100.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.100.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.101.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.101.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.101.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.102.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.102.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.102.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.103.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.103.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.103.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.104.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.104.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.104.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.105.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.105.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.105.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.106.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.106.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.106.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.107.w1.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.107.w2.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.107.w3.weight_scale": "model-00013-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.e_score_correction_bias": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.gate.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.0.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.0.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.0.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.1.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.1.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.1.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.10.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.10.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.10.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.10.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.10.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.10.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.100.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.100.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.100.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.100.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.100.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.100.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.101.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.101.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.101.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.101.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.101.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.101.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.102.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.102.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.102.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.102.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.102.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.102.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.103.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.103.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.103.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.103.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.103.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.103.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.104.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.104.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.104.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.104.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.104.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.104.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.105.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.105.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.105.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.105.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.105.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.105.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.106.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.106.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.106.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.106.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.106.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.106.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.107.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.107.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.107.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.107.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.107.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.107.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.108.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.108.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.108.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.108.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.108.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.108.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.109.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.109.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.109.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.109.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.109.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.109.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.11.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.11.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.11.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.11.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.11.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.11.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.110.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.110.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.110.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.110.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.110.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.110.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.111.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.111.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.111.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.111.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.111.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.111.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.112.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.112.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.112.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.112.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.112.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.112.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.113.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.113.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.113.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.113.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.113.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.113.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.114.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.114.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.114.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.114.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.114.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.114.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.115.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.115.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.115.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.115.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.115.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.115.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.116.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.116.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.116.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.116.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.116.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.116.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.117.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.117.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.117.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.117.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.117.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.117.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.118.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.118.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.118.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.118.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.118.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.118.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.119.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.119.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.119.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.119.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.119.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.119.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.12.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.12.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.12.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.12.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.12.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.12.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.120.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.120.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.120.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.120.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.120.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.120.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.121.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.121.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.121.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.121.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.121.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.121.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.122.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.122.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.122.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.122.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.122.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.122.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.123.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.123.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.123.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.123.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.123.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.123.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.124.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.124.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.124.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.124.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.124.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.124.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.125.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.125.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.125.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.125.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.125.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.125.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.126.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.126.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.126.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.126.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.126.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.126.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.127.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.127.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.127.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.127.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.127.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.127.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.13.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.13.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.13.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.13.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.13.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.13.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.14.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.14.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.14.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.14.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.14.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.14.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.15.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.15.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.15.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.15.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.15.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.15.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.16.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.16.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.16.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.16.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.16.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.16.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.17.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.17.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.17.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.17.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.17.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.17.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.18.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.18.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.18.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.18.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.18.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.18.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.19.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.19.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.19.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.19.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.19.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.19.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.2.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.2.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.2.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.20.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.20.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.20.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.20.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.20.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.20.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.21.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.21.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.21.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.21.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.21.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.21.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.22.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.22.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.22.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.22.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.22.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.22.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.23.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.23.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.23.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.23.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.23.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.23.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.24.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.24.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.24.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.24.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.24.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.24.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.25.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.25.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.25.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.25.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.25.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.25.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.26.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.26.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.26.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.26.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.26.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.26.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.27.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.27.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.27.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.27.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.27.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.27.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.28.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.28.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.28.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.28.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.28.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.28.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.29.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.29.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.29.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.29.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.29.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.29.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.3.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.3.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.3.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.30.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.30.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.30.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.30.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.30.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.30.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.31.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.31.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.31.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.31.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.31.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.31.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.32.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.32.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.32.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.32.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.32.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.32.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.33.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.33.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.33.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.33.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.33.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.33.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.34.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.34.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.34.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.34.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.34.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.34.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.35.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.35.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.35.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.35.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.35.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.35.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.36.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.36.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.36.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.36.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.36.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.36.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.37.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.37.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.37.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.37.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.37.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.37.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.38.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.38.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.38.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.38.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.38.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.38.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.39.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.39.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.39.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.39.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.39.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.39.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.4.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.4.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.4.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.40.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.40.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.40.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.40.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.40.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.40.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.41.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.41.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.41.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.41.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.41.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.41.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.42.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.42.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.42.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.42.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.42.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.42.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.43.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.43.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.43.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.43.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.43.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.43.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.44.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.44.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.44.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.44.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.44.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.44.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.45.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.45.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.45.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.45.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.45.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.45.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.46.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.46.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.46.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.46.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.46.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.46.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.47.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.47.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.47.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.47.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.47.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.47.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.48.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.48.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.48.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.48.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.48.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.48.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.49.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.49.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.49.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.49.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.49.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.49.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.5.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.5.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.5.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.50.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.50.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.50.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.50.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.50.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.50.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.51.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.51.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.51.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.51.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.51.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.51.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.52.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.52.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.52.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.52.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.52.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.52.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.53.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.53.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.53.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.53.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.53.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.53.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.54.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.54.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.54.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.54.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.54.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.54.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.55.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.55.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.55.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.55.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.55.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.55.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.56.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.56.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.56.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.56.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.56.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.56.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.57.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.57.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.57.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.57.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.57.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.57.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.58.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.58.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.58.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.58.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.58.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.58.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.59.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.59.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.59.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.59.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.59.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.59.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.6.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.6.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.6.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.60.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.60.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.60.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.60.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.60.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.60.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.61.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.61.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.61.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.61.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.61.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.61.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.62.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.62.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.62.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.62.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.62.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.62.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.63.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.63.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.63.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.63.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.63.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.63.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.64.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.64.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.64.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.64.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.64.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.64.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.65.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.65.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.65.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.65.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.65.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.65.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.66.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.66.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.66.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.66.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.66.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.66.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.67.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.67.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.67.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.67.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.67.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.67.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.68.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.68.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.68.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.68.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.68.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.68.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.69.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.69.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.69.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.69.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.69.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.69.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.7.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.7.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.7.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.70.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.70.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.70.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.70.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.70.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.70.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.71.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.71.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.71.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.71.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.71.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.71.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.72.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.72.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.72.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.72.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.72.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.72.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.73.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.73.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.73.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.73.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.73.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.73.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.74.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.74.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.74.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.74.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.74.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.74.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.75.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.75.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.75.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.75.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.75.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.75.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.76.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.76.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.76.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.76.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.76.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.76.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.77.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.77.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.77.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.77.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.77.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.77.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.78.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.78.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.78.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.78.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.78.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.78.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.79.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.79.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.79.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.79.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.79.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.79.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.8.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.8.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.8.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.8.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.8.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.8.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.80.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.80.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.80.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.80.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.80.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.80.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.81.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.81.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.81.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.81.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.81.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.81.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.82.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.82.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.82.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.82.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.82.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.82.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.83.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.83.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.83.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.83.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.83.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.83.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.84.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.84.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.84.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.84.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.84.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.84.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.85.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.85.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.85.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.85.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.85.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.85.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.86.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.86.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.86.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.86.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.86.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.86.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.87.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.87.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.87.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.87.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.87.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.87.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.88.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.88.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.88.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.88.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.88.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.88.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.89.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.89.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.89.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.89.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.89.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.89.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.9.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.9.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.9.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.9.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.9.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.9.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.90.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.90.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.90.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.90.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.90.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.90.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.91.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.91.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.91.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.91.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.91.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.91.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.92.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.92.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.92.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.92.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.92.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.92.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.93.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.93.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.93.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.93.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.93.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.93.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.94.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.94.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.94.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.94.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.94.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.94.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.95.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.95.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.95.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.95.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.95.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.95.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.96.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.96.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.96.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.96.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.96.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.96.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.97.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.97.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.97.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.97.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.97.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.97.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.98.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.98.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.98.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.98.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.98.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.98.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.99.w1.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.99.w1.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.99.w2.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.99.w2.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.99.w3.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.experts.99.w3.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.shared_experts.down_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.shared_experts.gate_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.shared_experts.up_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.post_attention_layernorm.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.index_k_norm.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.index_k_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.index_k_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.index_q_norm.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.index_q_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.index_q_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.k_norm.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.q_norm.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00031-of-00059.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight_scale": "model-00031-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.e_score_correction_bias": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.e_score_correction_bias": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.0.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.0.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.0.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.1.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.1.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.1.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.10.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.10.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.10.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.100.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.100.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.100.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.101.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.101.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.101.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.102.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.102.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.102.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.103.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.103.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.103.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.104.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.104.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.104.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.105.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.105.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.105.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.106.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.106.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.106.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.107.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.107.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.41.block_sparse_moe.experts.107.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.0.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.0.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.0.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.1.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.1.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.1.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.10.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.10.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.10.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.100.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.100.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.100.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.101.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.101.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.101.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.102.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.102.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.102.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.103.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.103.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.103.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.104.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.104.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.104.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.105.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.105.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.105.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.106.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.106.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.106.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.107.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.107.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.107.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.108.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.108.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.108.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.108.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.108.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.108.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.109.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.109.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.109.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.109.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.109.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.109.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.11.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.11.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.11.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.110.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.110.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.110.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.110.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.110.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.110.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.111.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.111.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.111.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.111.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.111.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.111.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.112.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.112.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.112.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.112.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.112.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.112.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.113.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.113.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.113.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.113.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.113.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.113.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.114.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.114.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.114.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.114.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.114.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.114.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.115.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.115.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.115.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.115.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.115.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.115.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.116.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.116.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.116.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.116.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.116.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.116.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.117.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.117.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.117.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.117.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.117.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.117.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.118.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.118.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.118.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.118.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.118.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.118.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.119.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.119.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.119.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.119.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.119.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.119.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.12.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.12.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.12.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.120.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.120.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.120.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.120.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.120.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.120.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.121.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.121.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.121.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.121.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.121.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.121.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.122.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.122.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.122.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.122.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.122.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.122.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.123.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.123.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.123.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.123.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.123.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.123.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.124.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.124.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.124.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.124.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.124.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.124.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.125.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.125.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.125.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.125.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.125.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.125.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.126.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.126.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.126.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.126.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.126.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.126.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.127.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.127.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.127.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.127.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.127.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.127.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.13.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.13.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.13.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.14.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.14.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.14.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.15.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.15.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.15.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.16.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.16.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.16.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.17.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.17.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.17.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.18.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.18.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.18.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.19.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.19.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.19.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.2.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.2.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.2.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.20.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.20.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.20.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.21.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.21.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.21.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.22.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.22.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.22.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.23.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.23.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.23.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.24.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.24.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.24.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.25.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.25.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.25.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.26.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.26.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.26.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.27.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.27.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.27.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.28.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.28.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.28.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.29.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.29.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.29.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.3.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.3.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.3.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.30.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.30.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.30.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.31.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.31.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.31.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.32.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.32.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.32.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.32.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.32.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.33.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.33.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.33.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.34.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.34.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.34.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.35.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.35.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.35.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.36.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.36.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.36.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.37.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.37.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.37.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.37.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.38.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.38.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.38.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.38.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.39.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.39.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.39.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.39.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.4.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.4.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.4.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.40.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.40.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.40.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.41.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.41.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.41.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.42.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.42.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.42.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.43.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.43.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.43.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.44.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.44.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.44.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.44.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.45.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.45.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.45.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.46.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.46.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.46.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.47.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.47.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.47.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.48.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.48.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.48.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.48.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.49.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.49.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.49.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.49.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.5.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.5.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.5.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.50.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.50.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.50.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.51.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.51.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.51.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.52.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.52.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.52.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.52.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.53.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.53.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.53.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.53.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.53.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.53.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.54.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.54.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.54.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.54.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.54.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.55.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.55.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.55.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.55.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.55.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.56.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.56.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.56.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.56.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.56.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.56.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.57.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.57.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.57.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.57.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.58.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.58.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.58.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.59.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.59.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.59.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.59.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.59.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.59.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.6.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.6.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.6.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.60.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.60.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.60.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.60.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.61.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.61.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.61.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.61.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.62.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.62.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.62.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.62.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.62.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.63.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.63.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.63.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.63.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.63.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.64.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.64.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.64.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.64.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.64.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.64.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.65.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.65.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.65.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.65.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.65.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.65.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.66.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.66.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.66.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.66.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.66.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.66.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.67.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.67.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.67.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.67.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.67.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.67.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.68.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.68.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.68.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.68.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.68.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.68.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.69.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.69.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.69.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.69.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.69.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.69.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.7.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.7.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.7.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.70.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.70.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.70.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.70.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.70.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.70.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.71.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.71.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.71.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.71.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.71.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.71.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.72.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.72.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.72.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.72.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.72.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.72.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.73.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.73.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.73.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.73.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.73.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.73.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.74.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.74.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.74.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.74.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.74.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.74.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.75.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.75.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.75.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.75.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.75.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.75.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.76.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.76.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.76.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.76.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.76.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.76.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.77.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.77.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.77.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.77.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.77.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.77.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.78.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.78.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.78.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.78.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.78.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.78.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.79.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.79.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.79.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.79.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.79.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.79.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.8.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.8.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.8.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.80.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.80.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.80.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.80.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.80.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.80.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.81.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.81.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.81.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.81.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.81.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.81.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.82.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.82.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.82.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.82.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.82.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.82.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.83.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.83.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.83.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.83.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.83.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.83.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.84.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.84.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.84.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.84.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.84.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.84.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.85.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.85.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.85.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.85.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.85.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.85.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.86.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.86.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.86.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.86.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.86.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.86.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.87.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.87.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.87.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.87.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.87.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.87.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.88.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.88.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.88.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.88.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.88.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.88.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.89.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.89.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.89.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.89.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.89.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.89.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.9.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.9.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.9.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.90.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.90.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.90.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.90.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.90.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.90.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.91.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.91.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.91.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.91.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.91.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.91.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.92.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.92.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.92.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.92.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.92.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.92.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.93.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.93.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.93.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.93.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.93.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.93.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.94.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.94.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.94.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.94.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.94.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.94.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.95.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.95.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.95.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.95.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.95.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.95.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.96.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.96.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.96.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.96.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.96.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.96.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.97.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.97.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.97.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.97.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.97.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.97.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.98.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.98.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.98.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.98.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.98.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.98.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.99.w1.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.99.w1.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.99.w2.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.99.w2.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.99.w3.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.experts.99.w3.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.shared_experts.down_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.shared_experts.gate_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.shared_experts.up_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.index_k_norm.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.index_k_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.index_k_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.index_q_norm.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.index_q_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.index_q_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.k_norm.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.q_norm.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00007-of-00059.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight_scale": "model-00007-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.e_score_correction_bias": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.gate.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.e_score_correction_bias": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.0.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.0.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.0.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.1.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.1.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.1.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.10.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.10.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.10.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.10.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.10.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.10.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.100.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.100.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.100.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.100.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.100.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.100.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.101.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.101.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.101.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.101.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.101.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.101.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.102.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.102.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.102.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.102.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.102.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.102.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.103.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.103.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.103.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.103.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.103.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.103.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.104.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.104.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.104.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.104.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.104.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.104.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.105.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.105.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.105.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.105.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.105.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.105.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.106.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.106.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.106.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.106.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.106.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.106.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.107.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.107.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.107.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.107.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.107.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.107.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.108.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.108.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.108.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.108.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.108.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.108.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.109.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.109.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.109.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.109.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.109.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.109.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.11.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.11.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.11.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.11.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.11.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.11.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.110.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.110.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.110.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.110.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.110.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.110.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.111.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.111.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.111.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.111.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.111.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.111.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.112.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.112.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.112.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.112.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.112.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.112.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.113.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.113.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.113.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.113.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.113.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.113.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.114.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.114.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.114.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.114.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.114.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.114.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.115.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.115.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.115.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.115.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.115.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.115.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.116.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.116.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.116.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.116.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.116.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.116.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.117.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.117.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.117.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.117.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.117.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.117.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.118.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.118.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.118.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.118.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.118.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.118.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.119.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.119.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.119.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.119.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.119.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.119.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.12.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.12.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.12.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.12.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.12.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.12.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.120.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.120.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.120.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.120.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.120.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.120.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.121.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.121.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.121.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.121.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.121.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.121.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.122.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.122.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.122.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.122.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.122.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.122.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.123.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.123.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.123.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.123.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.123.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.123.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.124.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.124.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.124.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.124.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.124.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.124.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.125.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.125.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.125.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.125.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.125.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.125.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.126.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.126.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.126.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.126.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.126.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.126.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.127.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.127.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.127.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.127.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.127.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.127.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.13.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.13.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.13.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.13.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.13.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.13.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.14.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.14.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.14.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.14.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.14.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.14.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.15.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.15.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.15.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.15.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.15.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.15.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.16.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.16.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.16.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.16.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.16.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.16.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.17.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.17.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.17.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.17.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.17.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.17.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.18.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.18.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.18.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.18.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.18.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.18.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.19.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.19.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.19.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.19.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.19.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.19.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.2.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.2.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.2.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.20.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.20.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.20.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.20.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.20.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.20.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.21.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.21.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.21.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.21.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.21.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.21.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.22.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.22.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.22.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.22.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.22.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.22.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.23.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.23.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.23.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.23.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.23.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.23.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.24.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.24.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.24.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.24.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.24.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.24.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.25.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.25.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.25.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.25.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.25.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.25.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.26.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.26.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.26.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.26.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.26.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.26.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.27.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.27.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.27.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.27.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.27.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.27.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.28.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.28.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.28.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.28.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.28.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.28.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.29.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.29.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.29.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.29.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.29.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.29.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.3.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.3.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.3.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.30.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.30.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.30.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.30.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.30.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.30.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.31.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.31.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.31.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.31.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.31.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.31.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.32.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.32.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.32.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.32.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.32.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.32.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.33.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.33.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.33.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.33.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.33.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.33.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.34.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.34.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.34.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.34.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.34.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.34.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.35.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.35.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.35.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.35.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.35.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.35.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.36.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.36.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.36.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.36.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.36.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.36.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.37.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.37.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.37.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.37.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.37.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.37.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.38.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.38.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.38.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.38.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.38.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.38.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.39.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.39.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.39.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.39.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.39.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.39.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.4.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.4.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.4.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.40.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.40.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.40.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.40.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.40.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.40.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.41.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.41.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.41.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.41.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.41.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.41.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.42.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.42.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.42.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.42.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.42.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.42.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.43.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.43.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.43.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.43.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.43.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.43.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.44.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.44.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.44.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.44.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.44.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.44.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.45.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.45.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.45.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.45.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.45.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.45.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.46.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.46.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.46.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.46.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.46.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.46.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.47.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.47.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.47.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.47.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.47.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.47.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.48.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.48.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.48.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.48.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.48.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.48.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.49.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.49.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.49.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.49.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.49.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.49.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.5.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.5.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.5.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.50.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.50.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.50.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.50.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.50.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.50.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.51.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.51.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.51.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.51.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.51.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.51.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.52.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.52.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.52.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.52.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.52.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.52.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.53.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.53.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.53.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.53.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.53.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.53.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.54.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.54.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.54.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.54.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.54.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.54.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.55.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.55.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.55.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.55.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.55.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.55.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.56.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.56.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.56.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.56.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.56.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.56.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.57.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.57.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.57.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.57.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.57.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.57.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.58.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.58.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.58.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.58.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.58.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.58.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.59.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.59.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.59.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.59.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.59.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.59.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.6.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.6.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.6.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.60.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.60.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.60.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.60.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.60.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.60.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.61.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.61.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.61.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.61.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.61.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.61.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.62.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.62.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.62.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.62.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.62.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.62.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.63.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.63.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.63.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.63.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.63.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.63.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.64.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.64.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.64.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.64.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.64.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.64.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.65.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.65.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.65.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.65.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.65.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.65.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.66.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.66.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.66.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.66.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.66.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.66.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.67.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.67.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.67.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.67.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.67.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.67.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.68.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.68.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.68.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.68.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.68.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.68.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.69.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.69.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.69.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.69.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.69.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.69.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.7.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.7.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.7.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.70.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.70.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.70.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.70.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.70.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.70.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.71.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.71.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.71.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.71.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.71.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.71.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.72.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.72.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.72.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.72.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.72.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.72.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.73.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.73.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.73.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.73.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.73.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.73.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.74.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.74.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.74.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.74.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.74.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.74.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.75.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.75.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.75.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.75.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.75.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.75.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.76.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.76.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.76.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.76.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.76.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.76.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.77.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.77.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.77.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.77.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.77.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.77.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.78.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.78.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.78.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.78.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.78.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.78.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.79.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.79.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.79.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.79.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.79.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.79.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.8.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.8.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.8.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.8.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.8.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.8.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.80.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.80.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.80.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.80.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.80.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.80.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.81.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.81.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.81.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.81.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.81.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.81.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.82.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.82.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.82.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.82.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.82.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.82.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.83.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.83.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.83.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.83.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.83.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.83.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.84.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.84.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.84.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.84.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.84.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.84.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.85.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.85.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.85.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.85.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.85.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.85.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.86.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.86.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.86.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.86.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.86.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.86.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.87.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.87.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.87.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.87.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.87.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.87.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.88.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.88.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.88.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.88.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.88.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.88.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.89.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.89.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.89.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.89.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.89.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.89.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.9.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.9.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.9.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.9.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.9.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.9.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.90.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.90.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.90.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.90.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.90.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.90.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.91.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.91.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.91.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.91.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.91.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.91.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.92.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.92.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.92.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.92.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.92.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.92.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.93.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.93.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.93.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.93.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.93.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.93.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.94.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.94.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.94.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.94.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.94.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.94.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.95.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.95.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.95.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.95.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.95.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.95.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.96.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.96.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.96.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.96.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.96.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.96.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.97.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.97.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.97.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.97.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.97.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.97.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.98.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.98.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.98.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.98.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.98.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.98.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.99.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.99.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.99.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.99.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.99.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.experts.99.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.shared_experts.down_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.shared_experts.gate_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.shared_experts.up_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.index_k_norm.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.index_k_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.index_k_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.index_q_norm.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.index_q_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.index_q_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.k_norm.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.q_norm.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.0.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.0.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.0.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.1.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.1.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.1.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.10.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.10.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.10.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.10.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.10.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.10.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.100.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.100.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.100.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.100.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.100.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.100.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.101.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.101.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.101.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.101.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.101.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.101.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.102.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.102.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.102.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.102.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.102.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.102.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.103.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.103.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.103.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.103.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.103.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.103.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.104.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.104.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.104.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.104.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.104.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.104.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.105.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.105.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.105.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.105.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.105.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.105.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.106.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.106.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.106.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.106.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.106.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.106.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.107.w1.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.107.w1.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.107.w2.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.107.w2.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.107.w3.weight": "model-00023-of-00059.safetensors", + "language_model.model.layers.57.block_sparse_moe.experts.107.w3.weight_scale": "model-00023-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.gate.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.108.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.108.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.108.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.108.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.108.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.108.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.109.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.109.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.109.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.109.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.109.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.109.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.11.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.11.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.11.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.11.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.11.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.11.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.110.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.110.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.110.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.110.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.110.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.110.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.111.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.111.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.111.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.111.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.111.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.111.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.112.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.112.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.112.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.112.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.112.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.112.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.113.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.113.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.113.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.113.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.113.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.113.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.114.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.114.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.114.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.114.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.114.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.114.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.115.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.115.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.115.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.115.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.115.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.115.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.116.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.116.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.116.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.116.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.116.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.116.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.117.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.117.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.117.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.117.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.117.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.117.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.118.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.118.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.118.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.118.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.118.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.118.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.119.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.119.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.119.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.119.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.119.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.119.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.12.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.12.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.12.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.12.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.12.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.12.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.120.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.120.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.120.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.120.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.120.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.120.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.121.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.121.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.121.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.121.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.121.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.121.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.122.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.122.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.122.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.122.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.122.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.122.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.123.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.123.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.123.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.123.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.123.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.123.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.124.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.124.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.124.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.124.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.124.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.124.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.125.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.125.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.125.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.125.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.125.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.125.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.126.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.126.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.126.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.126.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.126.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.126.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.127.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.127.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.127.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.127.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.127.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.127.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.13.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.13.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.13.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.13.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.13.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.13.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.14.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.14.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.14.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.14.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.14.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.14.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.15.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.15.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.15.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.15.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.15.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.15.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.16.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.16.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.16.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.16.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.16.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.16.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.17.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.17.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.17.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.17.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.17.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.17.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.18.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.18.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.18.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.18.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.18.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.18.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.19.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.19.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.19.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.19.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.19.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.19.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.2.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.2.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.2.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.20.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.20.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.20.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.20.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.20.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.20.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.21.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.21.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.21.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.21.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.21.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.21.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.22.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.22.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.22.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.22.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.22.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.22.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.23.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.23.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.23.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.23.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.23.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.23.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.24.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.24.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.24.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.24.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.24.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.24.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.25.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.25.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.25.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.25.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.25.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.25.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.26.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.26.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.26.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.26.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.26.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.26.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.27.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.27.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.27.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.27.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.27.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.27.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.28.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.28.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.28.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.28.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.28.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.28.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.29.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.29.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.29.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.29.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.29.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.29.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.3.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.3.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.3.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.30.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.30.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.30.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.30.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.30.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.30.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.31.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.31.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.31.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.31.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.31.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.31.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.32.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.32.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.32.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.32.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.32.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.32.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.33.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.33.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.33.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.33.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.33.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.33.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.34.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.34.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.34.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.34.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.34.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.34.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.35.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.35.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.35.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.35.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.35.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.35.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.36.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.36.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.36.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.36.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.36.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.36.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.37.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.37.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.37.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.37.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.37.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.37.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.38.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.38.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.38.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.38.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.38.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.38.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.39.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.39.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.39.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.39.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.39.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.39.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.4.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.4.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.4.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.40.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.40.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.40.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.40.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.40.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.40.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.41.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.41.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.41.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.41.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.41.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.41.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.42.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.42.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.42.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.42.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.42.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.42.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.43.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.43.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.43.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.43.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.43.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.43.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.44.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.44.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.44.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.44.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.44.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.44.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.45.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.45.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.45.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.45.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.45.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.45.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.46.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.46.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.46.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.46.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.46.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.46.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.47.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.47.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.47.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.47.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.47.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.47.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.48.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.48.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.48.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.48.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.48.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.48.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.49.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.49.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.49.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.49.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.49.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.49.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.5.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.5.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.5.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.5.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.5.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.5.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.50.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.50.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.50.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.50.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.50.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.50.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.51.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.51.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.51.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.51.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.51.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.51.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.52.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.52.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.52.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.52.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.52.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.52.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.53.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.53.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.53.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.53.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.53.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.53.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.54.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.54.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.54.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.54.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.54.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.54.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.55.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.55.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.55.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.55.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.55.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.55.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.56.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.56.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.56.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.56.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.56.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.56.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.57.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.57.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.57.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.57.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.57.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.57.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.58.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.58.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.58.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.58.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.58.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.58.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.59.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.59.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.59.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.59.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.59.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.59.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.6.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.6.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.6.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.6.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.6.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.6.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.60.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.60.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.60.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.60.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.60.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.60.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.61.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.61.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.61.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.61.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.61.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.61.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.62.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.62.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.62.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.62.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.62.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.62.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.63.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.63.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.63.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.63.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.63.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.63.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.64.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.64.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.64.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.64.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.64.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.64.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.65.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.65.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.65.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.65.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.65.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.65.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.66.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.66.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.66.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.66.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.66.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.66.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.67.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.67.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.67.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.67.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.67.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.67.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.68.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.68.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.68.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.68.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.68.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.68.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.69.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.69.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.69.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.69.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.69.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.69.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.7.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.7.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.7.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.7.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.7.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.7.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.70.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.70.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.70.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.70.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.70.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.70.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.71.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.71.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.71.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.71.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.71.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.71.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.72.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.72.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.72.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.72.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.72.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.72.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.73.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.73.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.73.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.73.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.73.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.73.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.74.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.74.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.74.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.74.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.74.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.74.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.75.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.75.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.75.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.75.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.75.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.75.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.76.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.76.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.76.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.76.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.76.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.76.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.77.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.77.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.77.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.77.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.77.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.77.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.78.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.78.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.78.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.78.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.78.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.78.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.79.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.79.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.79.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.79.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.79.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.79.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.8.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.8.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.8.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.8.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.8.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.8.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.80.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.80.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.80.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.80.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.80.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.80.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.81.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.81.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.81.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.81.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.81.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.81.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.82.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.82.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.82.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.82.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.82.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.82.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.83.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.83.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.83.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.83.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.83.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.83.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.84.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.84.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.84.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.84.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.84.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.84.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.85.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.85.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.85.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.85.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.85.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.85.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.86.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.86.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.86.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.86.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.86.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.86.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.87.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.87.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.87.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.87.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.87.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.87.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.88.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.88.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.88.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.88.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.88.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.88.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.89.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.89.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.89.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.89.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.89.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.89.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.9.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.9.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.9.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.9.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.9.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.9.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.90.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.90.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.90.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.90.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.90.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.90.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.91.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.91.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.91.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.91.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.91.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.91.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.92.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.92.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.92.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.92.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.92.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.92.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.93.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.93.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.93.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.93.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.93.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.93.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.94.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.94.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.94.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.94.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.94.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.94.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.95.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.95.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.95.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.95.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.95.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.95.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.96.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.96.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.96.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.96.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.96.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.96.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.97.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.97.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.97.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.97.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.97.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.97.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.98.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.98.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.98.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.98.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.98.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.98.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.99.w1.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.99.w1.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.99.w2.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.99.w2.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.99.w3.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.experts.99.w3.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.shared_experts.down_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.shared_experts.gate_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.shared_experts.up_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.input_layernorm.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.post_attention_layernorm.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.index_k_norm.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.index_k_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.index_k_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.index_q_norm.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.index_q_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.index_q_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.k_norm.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.k_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.k_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.o_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.o_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.q_norm.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.q_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.q_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.v_proj.weight": "model-00043-of-00059.safetensors", + "language_model.model.layers.43.self_attn.v_proj.weight_scale": "model-00043-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.e_score_correction_bias": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.e_score_correction_bias": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.0.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.0.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.0.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.1.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.1.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.1.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.10.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.10.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.10.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.100.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.100.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.100.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.101.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.101.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.101.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.102.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.102.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.102.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.103.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.103.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.103.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.104.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.104.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.104.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.105.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.105.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.105.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.106.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.106.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.106.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.107.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.107.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.107.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.108.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.108.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.108.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.108.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.108.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.108.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.109.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.109.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.109.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.109.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.109.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.109.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.11.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.11.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.11.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.110.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.110.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.110.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.110.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.110.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.110.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.111.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.111.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.111.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.111.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.111.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.111.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.112.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.112.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.112.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.112.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.112.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.112.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.113.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.113.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.113.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.113.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.113.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.113.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.114.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.114.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.114.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.114.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.114.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.114.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.115.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.115.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.115.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.115.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.115.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.115.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.116.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.116.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.116.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.116.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.116.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.116.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.117.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.117.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.117.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.117.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.117.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.117.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.118.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.118.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.118.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.118.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.118.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.118.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.119.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.119.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.119.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.119.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.119.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.119.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.12.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.12.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.12.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.120.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.120.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.120.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.120.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.120.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.120.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.121.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.121.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.121.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.121.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.121.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.121.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.122.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.122.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.122.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.122.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.122.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.122.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.123.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.123.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.123.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.123.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.123.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.123.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.124.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.124.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.124.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.124.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.124.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.124.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.125.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.125.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.125.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.125.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.125.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.125.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.126.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.126.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.126.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.126.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.126.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.126.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.127.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.127.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.127.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.127.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.127.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.127.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.13.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.13.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.13.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.14.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.14.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.14.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.15.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.15.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.15.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.16.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.16.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.16.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.17.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.17.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.17.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.18.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.18.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.18.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.19.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.19.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.19.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.2.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.2.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.2.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.20.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.20.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.20.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.21.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.21.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.21.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.22.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.22.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.22.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.23.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.23.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.23.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.24.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.24.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.24.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.25.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.25.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.25.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.26.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.26.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.26.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.27.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.27.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.27.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.28.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.28.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.28.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.29.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.29.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.29.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.3.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.3.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.3.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.30.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.30.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.30.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.31.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.31.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.31.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.32.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.32.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.32.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.32.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.32.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.32.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.33.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.33.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.33.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.33.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.33.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.33.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.34.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.34.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.34.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.34.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.34.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.34.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.35.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.35.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.35.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.35.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.35.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.35.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.36.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.36.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.36.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.36.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.36.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.36.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.37.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.37.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.37.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.37.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.37.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.37.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.38.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.38.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.38.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.38.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.38.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.38.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.39.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.39.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.39.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.39.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.39.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.39.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.4.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.4.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.4.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.40.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.40.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.40.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.40.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.40.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.40.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.41.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.41.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.41.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.41.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.41.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.41.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.42.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.42.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.42.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.42.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.42.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.42.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.43.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.43.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.43.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.43.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.43.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.43.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.44.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.44.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.44.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.44.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.44.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.44.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.45.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.45.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.45.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.45.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.45.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.45.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.46.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.46.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.46.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.46.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.46.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.46.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.47.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.47.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.47.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.47.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.47.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.47.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.48.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.48.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.48.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.48.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.48.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.48.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.49.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.49.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.49.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.49.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.49.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.49.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.5.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.5.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.5.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.50.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.50.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.50.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.50.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.50.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.50.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.51.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.51.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.51.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.51.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.51.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.51.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.52.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.52.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.52.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.52.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.52.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.52.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.53.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.53.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.53.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.53.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.53.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.53.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.54.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.54.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.54.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.54.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.54.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.54.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.55.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.55.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.55.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.55.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.55.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.55.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.56.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.56.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.56.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.56.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.56.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.56.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.57.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.57.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.57.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.57.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.57.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.57.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.58.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.58.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.58.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.58.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.58.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.58.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.59.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.59.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.59.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.59.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.59.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.59.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.6.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.6.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.6.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.60.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.60.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.60.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.60.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.60.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.60.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.61.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.61.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.61.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.61.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.61.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.61.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.62.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.62.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.62.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.62.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.62.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.62.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.63.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.63.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.63.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.63.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.63.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.63.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.64.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.64.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.64.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.64.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.64.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.64.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.65.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.65.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.65.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.65.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.65.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.65.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.66.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.66.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.66.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.66.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.66.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.66.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.67.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.67.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.67.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.67.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.67.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.67.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.68.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.68.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.68.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.68.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.68.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.68.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.69.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.69.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.69.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.69.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.69.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.69.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.7.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.7.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.7.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.70.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.70.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.70.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.70.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.70.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.70.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.71.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.71.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.71.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.71.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.71.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.71.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.72.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.72.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.72.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.72.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.72.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.72.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.73.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.73.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.73.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.73.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.73.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.73.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.74.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.74.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.74.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.74.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.74.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.74.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.75.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.75.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.75.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.75.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.75.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.75.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.76.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.76.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.76.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.76.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.76.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.76.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.77.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.77.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.77.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.77.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.77.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.77.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.78.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.78.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.78.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.78.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.78.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.78.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.79.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.79.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.79.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.79.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.79.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.79.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.8.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.8.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.8.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.80.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.80.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.80.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.80.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.80.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.80.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.81.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.81.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.81.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.81.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.81.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.81.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.82.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.82.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.82.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.82.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.82.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.82.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.83.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.83.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.83.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.83.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.83.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.83.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.84.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.84.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.84.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.84.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.84.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.84.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.85.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.85.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.85.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.85.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.85.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.85.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.86.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.86.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.86.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.86.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.86.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.86.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.87.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.87.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.87.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.87.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.87.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.87.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.88.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.88.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.88.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.88.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.88.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.88.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.89.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.89.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.89.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.89.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.89.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.89.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.9.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.9.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.9.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.90.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.90.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.90.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.90.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.90.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.90.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.91.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.91.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.91.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.91.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.91.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.91.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.92.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.92.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.92.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.92.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.93.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.93.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.93.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.94.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.94.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.94.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.95.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.95.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.95.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.96.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.96.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.96.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.97.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.97.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.97.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.98.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.98.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.98.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.99.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.99.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.experts.99.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.shared_experts.down_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.shared_experts.gate_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.shared_experts.up_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.index_k_norm.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.index_k_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.index_k_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.index_q_norm.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.index_q_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.index_q_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.k_norm.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.q_norm.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.0.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.0.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.0.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.1.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.1.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.1.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.10.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.10.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.10.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.100.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.100.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.100.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.101.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.101.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.101.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.102.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.102.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.102.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.103.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.103.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.103.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.104.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.104.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.104.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.105.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.105.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.105.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.106.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.106.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.106.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.107.w1.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.107.w2.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.107.w3.weight_scale": "model-00010-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.gate.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.108.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.108.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.108.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.108.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.108.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.108.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.109.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.109.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.109.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.109.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.109.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.109.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.11.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.11.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.11.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.11.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.11.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.11.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.110.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.110.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.110.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.110.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.110.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.110.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.111.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.111.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.111.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.111.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.111.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.111.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.112.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.112.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.112.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.112.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.112.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.112.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.113.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.113.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.113.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.113.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.113.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.113.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.114.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.114.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.114.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.114.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.114.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.114.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.115.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.115.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.115.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.115.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.115.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.115.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.116.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.116.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.116.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.116.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.116.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.116.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.117.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.117.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.117.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.117.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.117.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.117.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.118.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.118.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.118.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.118.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.118.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.118.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.119.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.119.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.119.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.119.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.119.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.119.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.12.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.12.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.12.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.12.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.12.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.12.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.120.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.120.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.120.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.120.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.120.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.120.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.121.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.121.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.121.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.121.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.121.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.121.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.122.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.122.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.122.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.122.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.122.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.122.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.123.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.123.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.123.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.123.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.123.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.123.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.124.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.124.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.124.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.124.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.124.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.124.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.125.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.125.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.125.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.125.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.125.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.125.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.126.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.126.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.126.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.126.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.126.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.126.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.127.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.127.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.127.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.127.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.127.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.127.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.13.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.13.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.13.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.13.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.13.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.13.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.14.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.14.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.14.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.14.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.14.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.14.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.15.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.15.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.15.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.15.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.15.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.15.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.16.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.16.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.16.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.16.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.16.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.16.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.17.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.17.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.17.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.17.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.17.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.17.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.18.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.18.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.18.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.18.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.18.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.18.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.19.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.19.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.19.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.19.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.19.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.19.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.2.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.2.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.2.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.2.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.2.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.2.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.20.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.20.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.20.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.20.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.20.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.20.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.21.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.21.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.21.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.21.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.21.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.21.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.22.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.22.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.22.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.22.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.22.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.22.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.23.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.23.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.23.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.23.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.23.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.23.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.24.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.24.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.24.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.24.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.24.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.24.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.25.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.25.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.25.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.25.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.25.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.25.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.26.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.26.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.26.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.26.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.26.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.26.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.27.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.27.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.27.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.27.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.27.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.27.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.28.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.28.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.28.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.28.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.28.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.28.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.29.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.29.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.29.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.29.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.29.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.29.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.3.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.3.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.3.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.3.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.3.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.3.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.30.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.30.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.30.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.30.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.30.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.30.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.31.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.31.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.31.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.31.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.31.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.31.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.32.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.32.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.32.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.32.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.32.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.32.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.33.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.33.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.33.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.33.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.33.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.33.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.34.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.34.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.34.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.34.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.34.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.34.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.35.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.35.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.35.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.35.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.35.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.35.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.36.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.36.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.36.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.36.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.36.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.36.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.37.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.37.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.37.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.37.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.37.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.37.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.38.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.38.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.38.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.38.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.38.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.38.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.39.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.39.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.39.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.39.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.39.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.39.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.4.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.4.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.4.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.4.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.4.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.4.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.40.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.40.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.40.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.40.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.40.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.40.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.41.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.41.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.41.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.41.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.41.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.41.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.42.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.42.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.42.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.42.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.42.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.42.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.43.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.43.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.43.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.43.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.43.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.43.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.44.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.44.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.44.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.44.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.44.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.44.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.45.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.45.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.45.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.45.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.45.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.45.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.46.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.46.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.46.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.46.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.46.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.46.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.47.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.47.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.47.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.47.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.47.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.47.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.48.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.48.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.48.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.48.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.48.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.48.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.49.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.49.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.49.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.49.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.49.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.49.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.5.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.5.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.5.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.5.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.5.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.5.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.50.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.50.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.50.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.50.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.50.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.50.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.51.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.51.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.51.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.51.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.51.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.51.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.52.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.52.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.52.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.52.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.52.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.52.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.53.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.53.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.53.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.53.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.53.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.53.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.54.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.54.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.54.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.54.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.54.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.54.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.55.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.55.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.55.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.55.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.55.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.55.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.56.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.56.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.56.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.56.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.56.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.56.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.57.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.57.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.57.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.57.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.57.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.57.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.58.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.58.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.58.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.58.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.58.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.58.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.59.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.59.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.59.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.59.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.59.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.59.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.6.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.6.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.6.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.6.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.6.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.6.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.60.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.60.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.60.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.60.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.60.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.60.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.61.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.61.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.61.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.61.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.61.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.61.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.62.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.62.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.62.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.62.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.62.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.62.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.63.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.63.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.63.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.63.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.63.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.63.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.64.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.64.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.64.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.64.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.64.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.64.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.65.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.65.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.65.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.65.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.65.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.65.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.66.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.66.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.66.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.66.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.66.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.66.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.67.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.67.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.67.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.67.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.67.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.67.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.68.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.68.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.68.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.68.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.68.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.68.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.69.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.69.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.69.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.69.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.69.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.69.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.7.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.7.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.7.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.7.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.7.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.7.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.70.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.70.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.70.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.70.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.70.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.70.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.71.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.71.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.71.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.71.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.71.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.71.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.72.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.72.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.72.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.72.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.72.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.72.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.73.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.73.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.73.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.73.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.73.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.73.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.74.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.74.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.74.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.74.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.74.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.74.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.75.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.75.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.75.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.75.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.75.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.75.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.76.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.76.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.76.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.76.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.76.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.76.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.77.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.77.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.77.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.77.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.77.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.77.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.78.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.78.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.78.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.78.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.78.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.78.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.79.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.79.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.79.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.79.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.79.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.79.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.8.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.8.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.8.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.8.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.8.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.8.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.80.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.80.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.80.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.80.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.80.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.80.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.81.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.81.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.81.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.81.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.81.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.81.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.82.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.82.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.82.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.82.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.82.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.82.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.83.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.83.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.83.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.83.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.83.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.83.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.84.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.84.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.84.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.84.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.84.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.84.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.85.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.85.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.85.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.85.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.85.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.85.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.86.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.86.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.86.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.86.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.86.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.86.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.87.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.87.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.87.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.87.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.87.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.87.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.88.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.88.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.88.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.88.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.88.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.88.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.89.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.89.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.89.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.89.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.89.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.89.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.9.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.9.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.9.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.9.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.9.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.9.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.90.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.90.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.90.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.90.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.90.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.90.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.91.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.91.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.91.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.91.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.91.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.91.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.92.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.92.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.92.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.92.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.92.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.92.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.93.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.93.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.93.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.93.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.93.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.93.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.94.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.94.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.94.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.94.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.94.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.94.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.95.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.95.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.95.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.95.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.95.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.95.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.96.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.96.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.96.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.96.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.96.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.96.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.97.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.97.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.97.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.97.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.97.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.97.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.98.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.98.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.98.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.98.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.98.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.98.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.99.w1.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.99.w1.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.99.w2.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.99.w2.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.99.w3.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.experts.99.w3.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.shared_experts.down_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.shared_experts.gate_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.shared_experts.up_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.input_layernorm.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.post_attention_layernorm.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.index_k_norm.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.index_k_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.index_k_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.index_q_norm.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.index_q_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.index_q_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.k_norm.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.k_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.k_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.o_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.o_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.q_norm.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.q_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.q_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.v_proj.weight": "model-00058-of-00059.safetensors", + "language_model.model.layers.58.self_attn.v_proj.weight_scale": "model-00058-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.e_score_correction_bias": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.gate.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.0.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.0.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.0.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.1.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.1.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.1.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.10.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.10.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.10.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.10.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.10.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.10.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.100.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.100.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.100.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.100.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.100.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.100.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.101.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.101.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.101.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.101.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.101.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.101.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.102.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.102.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.102.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.102.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.102.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.102.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.103.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.103.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.103.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.103.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.103.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.103.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.104.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.104.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.104.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.104.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.104.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.104.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.105.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.105.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.105.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.105.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.105.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.105.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.106.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.106.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.106.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.106.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.106.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.106.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.107.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.107.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.107.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.107.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.107.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.107.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.108.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.108.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.108.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.108.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.108.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.108.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.109.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.109.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.109.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.109.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.109.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.109.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.11.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.11.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.11.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.11.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.11.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.11.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.110.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.110.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.110.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.110.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.110.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.110.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.111.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.111.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.111.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.111.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.111.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.111.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.112.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.112.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.112.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.112.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.112.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.112.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.113.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.113.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.113.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.113.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.113.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.113.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.114.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.114.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.114.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.114.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.114.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.114.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.115.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.115.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.115.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.115.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.115.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.115.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.116.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.116.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.116.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.116.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.116.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.116.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.117.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.117.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.117.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.117.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.117.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.117.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.118.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.118.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.118.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.118.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.118.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.118.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.119.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.119.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.119.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.119.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.119.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.119.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.12.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.12.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.12.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.12.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.12.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.12.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.120.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.120.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.120.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.120.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.120.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.120.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.121.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.121.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.121.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.121.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.121.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.121.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.122.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.122.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.122.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.122.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.122.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.122.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.123.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.123.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.123.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.123.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.123.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.123.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.124.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.124.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.124.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.124.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.124.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.124.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.125.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.125.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.125.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.125.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.125.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.125.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.126.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.126.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.126.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.126.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.126.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.126.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.127.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.127.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.127.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.127.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.127.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.127.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.13.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.13.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.13.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.13.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.13.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.13.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.14.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.14.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.14.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.14.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.14.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.14.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.15.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.15.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.15.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.15.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.15.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.15.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.16.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.16.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.16.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.16.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.16.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.16.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.17.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.17.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.17.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.17.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.17.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.17.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.18.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.18.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.18.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.18.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.18.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.18.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.19.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.19.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.19.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.19.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.19.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.19.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.2.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.2.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.2.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.20.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.20.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.20.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.20.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.20.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.20.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.21.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.21.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.21.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.21.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.21.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.21.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.22.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.22.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.22.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.22.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.22.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.22.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.23.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.23.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.23.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.23.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.23.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.23.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.24.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.24.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.24.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.24.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.24.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.24.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.25.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.25.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.25.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.25.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.25.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.25.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.26.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.26.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.26.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.26.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.26.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.26.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.27.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.27.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.27.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.27.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.27.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.27.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.28.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.28.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.28.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.28.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.28.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.28.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.29.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.29.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.29.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.29.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.29.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.29.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.3.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.3.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.3.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.30.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.30.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.30.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.30.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.30.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.30.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.31.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.31.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.31.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.31.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.31.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.31.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.32.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.32.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.32.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.32.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.32.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.32.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.33.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.33.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.33.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.33.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.33.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.33.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.34.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.34.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.34.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.34.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.34.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.34.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.35.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.35.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.35.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.35.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.35.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.35.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.36.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.36.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.36.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.36.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.36.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.36.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.37.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.37.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.37.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.37.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.37.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.37.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.38.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.38.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.38.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.38.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.38.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.38.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.39.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.39.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.39.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.39.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.39.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.39.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.4.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.4.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.4.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.40.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.40.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.40.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.40.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.40.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.40.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.41.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.41.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.41.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.41.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.41.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.41.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.42.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.42.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.42.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.42.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.42.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.42.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.43.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.43.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.43.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.43.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.43.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.43.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.44.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.44.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.44.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.44.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.44.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.44.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.45.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.45.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.45.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.45.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.45.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.45.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.46.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.46.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.46.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.46.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.46.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.46.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.47.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.47.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.47.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.47.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.47.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.47.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.48.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.48.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.48.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.48.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.48.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.48.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.49.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.49.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.49.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.49.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.49.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.49.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.5.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.5.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.5.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.50.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.50.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.50.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.50.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.50.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.50.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.51.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.51.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.51.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.51.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.51.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.51.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.52.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.52.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.52.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.52.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.52.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.52.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.53.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.53.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.53.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.53.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.53.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.53.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.54.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.54.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.54.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.54.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.54.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.54.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.55.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.55.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.55.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.55.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.55.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.55.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.56.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.56.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.56.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.56.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.56.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.56.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.57.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.57.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.57.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.57.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.57.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.57.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.58.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.58.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.58.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.58.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.58.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.58.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.59.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.59.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.59.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.59.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.59.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.59.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.6.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.6.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.6.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.60.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.60.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.60.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.60.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.60.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.60.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.61.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.61.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.61.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.61.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.61.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.61.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.62.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.62.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.62.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.62.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.62.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.62.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.63.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.63.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.63.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.63.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.63.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.63.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.64.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.64.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.64.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.64.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.64.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.64.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.65.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.65.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.65.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.65.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.65.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.65.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.66.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.66.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.66.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.66.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.66.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.66.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.67.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.67.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.67.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.67.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.67.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.67.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.68.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.68.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.68.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.68.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.68.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.68.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.69.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.69.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.69.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.69.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.69.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.69.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.7.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.7.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.7.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.70.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.70.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.70.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.70.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.70.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.70.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.71.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.71.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.71.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.71.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.71.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.71.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.72.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.72.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.72.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.72.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.72.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.72.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.73.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.73.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.73.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.73.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.73.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.73.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.74.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.74.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.74.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.74.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.74.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.74.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.75.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.75.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.75.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.75.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.75.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.75.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.76.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.76.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.76.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.76.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.76.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.76.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.77.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.77.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.77.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.77.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.77.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.77.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.78.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.78.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.78.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.78.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.78.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.78.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.79.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.79.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.79.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.79.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.79.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.79.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.8.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.8.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.8.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.8.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.8.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.8.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.80.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.80.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.80.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.80.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.80.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.80.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.81.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.81.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.81.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.81.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.81.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.81.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.82.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.82.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.82.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.82.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.82.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.82.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.83.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.83.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.83.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.83.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.83.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.83.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.84.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.84.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.84.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.84.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.84.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.84.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.85.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.85.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.85.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.85.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.85.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.85.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.86.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.86.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.86.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.86.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.86.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.86.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.87.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.87.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.87.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.87.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.87.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.87.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.88.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.88.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.88.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.88.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.88.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.88.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.89.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.89.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.89.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.89.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.89.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.89.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.9.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.9.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.9.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.9.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.9.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.9.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.90.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.90.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.90.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.90.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.90.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.90.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.91.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.91.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.91.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.91.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.91.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.91.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.92.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.92.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.92.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.92.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.92.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.92.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.93.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.93.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.93.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.93.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.93.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.93.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.94.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.94.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.94.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.94.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.94.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.94.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.95.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.95.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.95.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.95.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.95.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.95.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.96.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.96.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.96.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.96.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.96.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.96.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.97.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.97.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.97.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.97.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.97.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.97.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.98.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.98.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.98.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.98.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.98.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.98.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.99.w1.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.99.w1.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.99.w2.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.99.w2.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.99.w3.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.experts.99.w3.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.shared_experts.down_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.shared_experts.gate_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.shared_experts.up_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.index_k_norm.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.index_k_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.index_k_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.index_q_norm.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.index_q_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.index_q_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.k_norm.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.o_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.o_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.q_norm.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight": "model-00028-of-00059.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight_scale": "model-00028-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.e_score_correction_bias": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.e_score_correction_bias": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.0.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.0.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.0.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.1.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.1.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.1.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.10.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.10.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.10.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.100.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.100.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.100.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.101.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.101.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.101.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.102.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.102.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.102.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.103.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.103.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.103.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.104.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.104.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.104.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.105.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.105.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.105.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.106.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.106.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.106.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.107.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.107.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.42.block_sparse_moe.experts.107.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.0.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.0.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.0.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.1.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.1.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.1.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.10.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.10.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.10.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.100.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.100.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.100.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.101.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.101.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.101.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.102.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.102.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.102.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.103.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.103.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.103.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.104.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.104.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.104.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.105.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.105.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.105.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.106.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.106.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.106.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.107.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.107.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.107.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.108.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.108.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.108.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.108.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.108.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.108.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.109.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.109.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.109.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.109.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.109.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.109.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.11.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.11.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.11.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.110.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.110.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.110.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.110.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.110.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.110.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.111.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.111.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.111.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.111.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.111.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.111.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.112.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.112.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.112.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.112.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.112.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.112.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.113.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.113.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.113.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.113.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.113.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.113.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.114.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.114.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.114.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.114.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.114.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.114.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.115.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.115.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.115.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.115.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.115.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.115.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.116.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.116.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.116.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.116.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.116.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.116.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.117.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.117.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.117.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.117.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.117.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.117.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.118.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.118.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.118.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.118.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.118.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.118.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.119.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.119.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.119.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.119.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.119.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.119.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.12.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.12.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.12.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.120.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.120.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.120.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.120.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.120.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.120.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.121.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.121.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.121.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.121.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.121.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.121.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.122.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.122.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.122.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.122.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.122.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.122.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.123.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.123.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.123.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.123.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.123.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.123.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.124.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.124.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.124.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.124.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.124.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.124.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.125.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.125.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.125.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.125.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.125.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.125.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.126.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.126.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.126.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.126.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.126.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.126.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.127.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.127.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.127.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.127.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.127.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.127.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.13.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.13.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.13.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.14.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.14.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.14.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.15.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.15.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.15.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.16.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.16.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.16.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.17.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.17.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.17.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.18.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.18.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.18.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.19.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.19.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.19.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.2.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.2.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.2.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.20.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.20.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.20.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.21.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.21.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.21.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.22.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.22.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.22.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.23.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.23.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.23.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.24.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.24.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.24.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.25.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.25.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.25.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.26.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.26.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.26.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.27.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.27.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.27.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.28.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.28.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.28.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.29.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.29.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.29.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.3.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.3.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.3.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.30.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.30.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.30.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.31.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.31.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.31.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.32.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.32.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.32.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.32.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.32.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.32.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.33.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.33.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.33.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.33.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.33.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.33.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.34.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.34.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.34.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.34.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.34.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.34.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.35.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.35.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.35.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.35.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.35.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.35.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.36.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.36.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.36.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.36.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.36.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.36.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.37.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.37.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.37.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.37.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.37.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.37.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.38.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.38.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.38.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.38.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.38.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.38.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.39.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.39.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.39.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.39.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.39.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.39.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.4.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.4.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.4.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.40.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.40.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.40.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.40.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.40.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.40.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.41.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.41.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.41.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.41.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.41.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.41.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.42.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.42.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.42.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.42.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.42.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.42.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.43.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.43.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.43.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.43.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.43.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.43.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.44.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.44.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.44.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.44.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.44.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.44.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.45.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.45.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.45.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.45.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.45.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.45.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.46.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.46.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.46.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.46.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.46.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.46.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.47.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.47.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.47.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.47.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.47.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.47.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.48.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.48.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.48.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.48.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.48.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.48.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.49.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.49.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.49.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.49.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.49.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.49.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.5.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.5.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.5.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.50.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.50.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.50.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.50.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.50.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.50.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.51.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.51.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.51.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.51.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.51.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.51.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.52.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.52.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.52.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.52.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.52.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.52.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.53.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.53.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.53.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.54.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.54.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.54.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.54.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.54.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.54.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.55.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.55.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.55.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.55.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.55.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.55.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.56.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.56.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.56.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.56.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.56.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.56.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.57.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.57.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.57.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.57.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.57.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.57.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.58.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.58.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.58.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.58.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.58.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.58.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.59.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.59.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.59.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.59.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.59.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.59.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.6.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.6.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.6.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.60.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.60.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.60.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.60.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.60.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.60.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.61.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.61.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.61.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.61.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.61.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.61.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.62.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.62.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.62.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.62.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.62.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.62.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.63.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.63.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.63.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.63.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.63.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.63.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.64.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.64.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.64.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.64.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.64.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.64.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.65.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.65.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.65.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.65.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.65.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.65.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.66.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.66.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.66.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.66.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.66.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.66.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.67.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.67.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.67.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.67.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.67.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.67.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.68.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.68.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.68.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.68.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.68.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.68.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.69.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.69.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.69.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.69.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.69.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.69.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.7.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.7.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.7.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.70.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.70.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.70.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.70.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.70.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.70.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.71.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.71.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.71.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.71.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.71.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.71.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.72.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.72.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.72.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.72.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.72.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.72.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.73.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.73.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.73.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.73.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.73.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.73.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.74.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.74.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.74.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.74.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.74.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.74.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.75.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.75.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.75.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.75.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.75.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.75.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.76.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.76.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.76.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.76.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.76.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.76.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.77.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.77.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.77.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.77.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.77.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.77.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.78.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.78.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.78.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.78.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.78.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.78.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.79.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.79.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.79.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.79.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.79.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.79.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.8.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.8.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.8.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.80.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.80.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.80.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.80.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.80.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.80.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.81.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.81.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.81.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.81.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.81.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.81.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.82.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.82.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.82.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.82.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.82.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.82.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.83.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.83.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.83.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.83.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.83.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.83.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.84.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.84.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.84.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.84.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.84.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.84.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.85.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.85.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.85.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.85.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.85.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.85.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.86.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.86.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.86.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.86.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.86.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.86.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.87.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.87.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.87.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.87.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.87.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.87.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.88.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.88.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.88.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.88.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.88.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.88.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.89.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.89.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.89.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.89.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.89.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.89.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.9.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.9.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.9.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.90.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.90.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.90.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.90.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.90.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.90.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.91.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.91.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.91.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.91.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.91.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.91.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.92.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.92.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.92.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.92.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.92.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.92.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.93.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.93.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.93.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.93.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.93.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.93.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.94.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.94.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.94.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.94.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.94.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.94.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.95.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.95.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.95.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.95.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.95.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.95.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.96.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.96.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.96.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.96.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.96.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.96.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.97.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.97.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.97.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.97.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.97.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.97.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.98.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.98.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.98.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.98.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.98.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.98.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.99.w1.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.99.w1.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.99.w2.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.99.w2.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.99.w3.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.experts.99.w3.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.shared_experts.down_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.shared_experts.gate_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.shared_experts.up_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.index_k_norm.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.index_k_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.index_k_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.index_q_norm.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.index_q_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.index_q_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.k_norm.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.q_norm.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00008-of-00059.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight_scale": "model-00008-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.gate.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.108.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.108.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.108.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.108.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.108.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.108.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.109.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.109.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.109.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.109.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.109.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.109.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.11.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.11.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.11.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.11.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.11.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.11.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.110.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.110.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.110.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.110.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.110.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.110.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.111.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.111.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.111.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.111.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.111.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.111.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.112.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.112.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.112.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.112.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.112.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.112.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.113.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.113.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.113.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.113.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.113.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.113.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.114.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.114.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.114.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.114.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.114.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.114.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.115.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.115.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.115.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.115.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.115.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.115.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.116.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.116.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.116.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.116.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.116.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.116.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.117.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.117.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.117.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.117.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.117.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.117.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.118.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.118.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.118.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.118.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.118.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.118.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.119.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.119.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.119.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.119.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.119.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.119.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.12.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.12.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.12.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.12.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.12.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.12.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.120.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.120.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.120.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.120.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.120.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.120.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.121.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.121.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.121.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.121.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.121.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.121.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.122.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.122.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.122.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.122.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.122.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.122.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.123.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.123.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.123.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.123.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.123.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.123.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.124.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.124.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.124.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.124.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.124.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.124.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.125.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.125.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.125.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.125.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.125.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.125.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.126.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.126.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.126.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.126.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.126.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.126.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.127.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.127.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.127.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.127.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.127.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.127.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.13.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.13.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.13.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.13.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.13.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.13.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.14.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.14.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.14.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.14.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.14.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.14.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.15.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.15.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.15.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.15.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.15.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.15.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.16.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.16.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.16.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.16.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.16.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.16.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.17.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.17.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.17.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.17.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.17.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.17.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.18.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.18.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.18.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.18.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.18.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.18.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.19.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.19.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.19.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.19.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.19.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.19.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.2.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.2.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.2.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.20.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.20.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.20.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.20.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.20.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.20.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.21.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.21.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.21.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.21.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.21.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.21.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.22.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.22.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.22.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.22.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.22.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.22.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.23.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.23.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.23.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.23.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.23.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.23.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.24.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.24.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.24.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.24.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.24.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.24.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.25.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.25.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.25.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.25.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.25.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.25.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.26.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.26.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.26.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.26.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.26.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.26.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.27.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.27.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.27.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.27.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.27.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.27.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.28.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.28.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.28.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.28.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.28.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.28.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.29.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.29.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.29.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.29.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.29.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.29.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.3.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.3.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.3.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.3.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.3.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.3.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.30.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.30.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.30.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.30.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.30.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.30.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.31.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.31.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.31.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.31.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.31.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.31.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.32.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.32.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.32.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.32.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.32.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.32.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.33.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.33.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.33.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.33.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.33.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.33.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.34.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.34.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.34.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.34.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.34.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.34.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.35.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.35.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.35.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.35.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.35.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.35.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.36.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.36.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.36.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.36.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.36.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.36.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.37.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.37.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.37.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.37.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.37.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.37.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.38.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.38.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.38.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.38.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.38.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.38.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.39.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.39.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.39.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.39.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.39.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.39.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.4.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.4.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.4.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.4.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.4.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.4.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.40.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.40.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.40.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.40.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.40.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.40.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.41.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.41.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.41.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.41.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.41.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.41.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.42.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.42.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.42.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.42.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.42.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.42.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.43.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.43.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.43.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.43.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.43.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.43.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.44.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.44.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.44.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.44.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.44.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.44.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.45.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.45.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.45.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.45.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.45.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.45.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.46.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.46.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.46.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.46.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.46.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.46.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.47.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.47.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.47.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.47.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.47.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.47.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.48.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.48.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.48.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.48.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.48.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.48.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.49.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.49.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.49.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.49.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.49.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.49.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.5.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.5.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.5.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.5.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.5.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.5.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.50.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.50.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.50.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.50.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.50.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.50.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.51.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.51.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.51.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.51.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.51.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.51.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.52.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.52.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.52.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.52.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.52.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.52.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.53.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.53.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.53.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.53.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.53.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.53.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.54.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.54.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.54.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.54.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.54.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.54.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.55.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.55.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.55.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.55.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.55.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.55.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.56.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.56.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.56.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.56.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.56.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.56.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.57.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.57.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.57.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.57.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.57.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.57.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.58.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.58.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.58.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.58.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.58.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.58.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.59.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.59.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.59.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.59.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.59.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.59.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.6.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.6.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.6.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.6.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.6.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.6.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.60.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.60.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.60.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.60.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.60.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.60.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.61.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.61.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.61.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.61.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.61.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.61.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.62.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.62.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.62.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.62.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.62.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.62.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.63.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.63.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.63.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.63.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.63.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.63.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.64.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.64.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.64.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.64.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.64.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.64.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.65.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.65.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.65.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.65.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.65.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.65.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.66.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.66.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.66.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.66.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.66.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.66.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.67.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.67.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.67.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.67.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.67.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.67.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.68.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.68.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.68.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.68.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.68.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.68.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.69.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.69.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.69.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.69.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.69.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.69.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.7.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.7.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.7.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.7.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.7.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.7.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.70.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.70.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.70.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.70.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.70.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.70.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.71.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.71.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.71.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.71.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.71.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.71.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.72.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.72.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.72.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.72.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.72.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.72.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.73.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.73.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.73.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.73.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.73.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.73.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.74.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.74.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.74.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.74.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.74.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.74.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.75.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.75.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.75.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.75.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.75.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.75.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.76.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.76.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.76.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.76.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.76.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.76.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.77.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.77.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.77.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.77.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.77.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.77.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.78.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.78.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.78.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.78.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.78.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.78.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.79.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.79.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.79.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.79.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.79.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.79.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.8.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.8.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.8.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.8.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.8.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.8.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.80.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.80.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.80.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.80.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.80.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.80.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.81.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.81.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.81.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.81.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.81.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.81.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.82.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.82.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.82.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.82.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.82.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.82.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.83.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.83.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.83.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.83.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.83.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.83.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.84.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.84.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.84.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.84.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.84.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.84.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.85.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.85.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.85.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.85.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.85.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.85.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.86.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.86.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.86.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.86.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.86.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.86.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.87.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.87.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.87.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.87.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.87.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.87.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.88.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.88.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.88.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.88.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.88.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.88.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.89.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.89.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.89.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.89.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.89.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.89.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.9.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.9.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.9.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.9.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.9.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.9.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.90.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.90.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.90.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.90.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.90.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.90.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.91.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.91.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.91.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.91.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.91.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.91.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.92.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.92.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.92.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.92.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.92.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.92.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.93.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.93.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.93.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.93.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.93.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.93.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.94.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.94.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.94.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.94.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.94.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.94.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.95.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.95.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.95.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.95.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.95.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.95.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.96.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.96.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.96.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.96.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.96.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.96.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.97.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.97.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.97.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.97.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.97.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.97.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.98.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.98.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.98.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.98.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.98.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.98.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.99.w1.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.99.w1.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.99.w2.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.99.w2.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.99.w3.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.99.w3.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.shared_experts.down_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.shared_experts.gate_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.shared_experts.up_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.input_layernorm.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.post_attention_layernorm.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.index_k_norm.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.index_k_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.index_k_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.index_q_norm.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.index_q_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.index_q_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.k_norm.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.k_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.k_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.o_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.o_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.q_norm.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.q_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.q_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.v_proj.weight": "model-00050-of-00059.safetensors", + "language_model.model.layers.50.self_attn.v_proj.weight_scale": "model-00050-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.e_score_correction_bias": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.e_score_correction_bias": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.0.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.0.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.0.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.1.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.1.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.1.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.10.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.10.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.10.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.100.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.100.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.100.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.101.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.101.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.101.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.102.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.102.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.102.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.103.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.103.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.103.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.104.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.104.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.104.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.105.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.105.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.105.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.106.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.106.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.106.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.107.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.107.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.40.block_sparse_moe.experts.107.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.0.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.0.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.0.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.1.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.1.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.1.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.10.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.10.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.10.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.100.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.100.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.100.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.101.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.101.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.101.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.102.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.102.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.102.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.103.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.103.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.103.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.104.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.104.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.104.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.105.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.105.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.105.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.106.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.106.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.106.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.107.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.107.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.107.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.108.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.108.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.108.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.108.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.108.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.108.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.109.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.109.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.109.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.109.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.109.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.109.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.11.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.11.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.11.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.110.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.110.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.110.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.110.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.110.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.110.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.111.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.111.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.111.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.111.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.111.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.111.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.112.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.112.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.112.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.112.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.112.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.112.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.113.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.113.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.113.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.113.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.113.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.113.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.114.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.114.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.114.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.114.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.114.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.114.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.115.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.115.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.115.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.115.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.115.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.115.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.116.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.116.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.116.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.116.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.116.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.116.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.117.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.117.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.117.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.117.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.117.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.117.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.118.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.118.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.118.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.118.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.118.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.118.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.119.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.119.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.119.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.119.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.119.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.119.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.12.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.12.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.12.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.120.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.120.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.120.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.120.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.120.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.120.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.121.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.121.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.121.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.121.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.121.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.121.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.122.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.122.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.122.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.122.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.122.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.122.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.123.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.123.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.123.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.123.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.123.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.123.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.124.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.124.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.124.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.124.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.124.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.124.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.125.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.125.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.125.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.125.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.125.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.125.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.126.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.126.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.126.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.126.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.126.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.126.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.127.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.127.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.127.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.127.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.127.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.127.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.13.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.13.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.13.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.14.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.14.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.14.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.15.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.15.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.15.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.16.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.16.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.16.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.17.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.17.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.17.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.18.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.18.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.18.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.19.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.19.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.19.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.2.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.2.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.2.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.20.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.20.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.20.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.21.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.21.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.21.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.22.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.22.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.22.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.23.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.23.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.23.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.24.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.24.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.24.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.25.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.25.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.25.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.26.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.26.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.26.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.27.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.27.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.27.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.28.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.28.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.28.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.29.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.29.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.29.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.3.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.3.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.3.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.30.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.30.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.30.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.31.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.31.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.31.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.32.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.32.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.32.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.33.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.33.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.33.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.34.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.34.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.34.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.35.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.35.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.35.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.36.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.36.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.36.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.37.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.37.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.37.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.38.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.38.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.38.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.39.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.39.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.39.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.4.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.4.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.4.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.40.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.40.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.40.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.41.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.41.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.41.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.42.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.42.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.42.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.43.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.43.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.43.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.44.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.44.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.44.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.45.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.45.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.45.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.46.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.46.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.46.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.47.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.47.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.47.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.48.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.48.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.48.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.49.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.49.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.49.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.49.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.5.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.5.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.5.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.50.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.50.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.50.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.51.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.51.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.51.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.52.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.52.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.52.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.53.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.53.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.53.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.54.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.54.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.54.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.55.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.55.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.55.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.56.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.56.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.56.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.57.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.57.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.57.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.58.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.58.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.58.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.59.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.59.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.59.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.6.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.6.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.6.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.60.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.60.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.60.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.61.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.61.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.61.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.62.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.62.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.62.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.63.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.63.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.63.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.64.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.64.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.64.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.64.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.64.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.64.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.65.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.65.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.65.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.65.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.65.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.65.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.66.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.66.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.66.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.66.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.66.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.66.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.67.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.67.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.67.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.67.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.67.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.67.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.68.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.68.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.68.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.68.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.68.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.68.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.69.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.69.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.69.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.69.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.69.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.69.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.7.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.7.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.7.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.70.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.70.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.70.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.70.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.70.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.70.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.71.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.71.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.71.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.71.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.71.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.71.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.72.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.72.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.72.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.72.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.72.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.72.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.73.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.73.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.73.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.73.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.73.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.73.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.74.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.74.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.74.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.74.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.74.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.74.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.75.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.75.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.75.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.75.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.75.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.75.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.76.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.76.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.76.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.76.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.76.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.76.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.77.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.77.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.77.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.77.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.77.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.77.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.78.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.78.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.78.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.78.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.78.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.78.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.79.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.79.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.79.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.79.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.79.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.79.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.8.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.8.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.8.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.80.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.80.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.80.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.80.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.80.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.80.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.81.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.81.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.81.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.81.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.81.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.81.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.82.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.82.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.82.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.82.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.82.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.82.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.83.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.83.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.83.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.83.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.83.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.83.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.84.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.84.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.84.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.84.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.84.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.84.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.85.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.85.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.85.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.85.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.85.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.85.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.86.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.86.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.86.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.86.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.86.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.86.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.87.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.87.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.87.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.87.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.87.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.87.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.88.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.88.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.88.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.88.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.88.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.88.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.89.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.89.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.89.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.89.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.89.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.89.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.9.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.9.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.9.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.90.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.90.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.90.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.90.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.90.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.90.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.91.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.91.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.91.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.91.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.91.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.91.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.92.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.92.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.92.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.92.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.92.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.92.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.93.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.93.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.93.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.93.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.93.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.93.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.94.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.94.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.94.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.94.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.94.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.94.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.95.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.95.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.95.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.95.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.95.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.95.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.96.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.96.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.96.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.96.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.96.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.96.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.97.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.97.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.97.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.97.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.97.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.97.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.98.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.98.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.98.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.98.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.98.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.98.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.99.w1.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.99.w1.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.99.w2.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.99.w2.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.99.w3.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.experts.99.w3.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.shared_experts.down_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.shared_experts.gate_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.shared_experts.up_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.index_k_norm.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.index_k_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.index_k_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.index_q_norm.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.index_q_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.index_q_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.k_norm.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.q_norm.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00006-of-00059.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight_scale": "model-00006-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.gate.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.108.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.108.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.108.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.108.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.108.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.108.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.109.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.109.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.109.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.109.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.109.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.109.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.11.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.11.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.11.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.11.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.11.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.11.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.110.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.110.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.110.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.110.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.110.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.110.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.111.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.111.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.111.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.111.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.111.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.111.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.112.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.112.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.112.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.112.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.112.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.112.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.113.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.113.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.113.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.113.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.113.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.113.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.114.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.114.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.114.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.114.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.114.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.114.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.115.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.115.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.115.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.115.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.115.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.115.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.116.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.116.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.116.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.116.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.116.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.116.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.117.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.117.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.117.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.117.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.117.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.117.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.118.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.118.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.118.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.118.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.118.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.118.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.119.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.119.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.119.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.119.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.119.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.119.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.12.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.12.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.12.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.12.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.12.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.12.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.120.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.120.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.120.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.120.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.120.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.120.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.121.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.121.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.121.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.121.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.121.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.121.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.122.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.122.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.122.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.122.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.122.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.122.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.123.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.123.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.123.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.123.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.123.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.123.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.124.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.124.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.124.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.124.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.124.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.124.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.125.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.125.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.125.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.125.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.125.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.125.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.126.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.126.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.126.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.126.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.126.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.126.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.127.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.127.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.127.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.127.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.127.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.127.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.13.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.13.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.13.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.13.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.13.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.13.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.14.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.14.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.14.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.14.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.14.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.14.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.15.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.15.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.15.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.15.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.15.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.15.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.16.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.16.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.16.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.16.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.16.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.16.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.17.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.17.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.17.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.17.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.17.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.17.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.18.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.18.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.18.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.18.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.18.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.18.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.19.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.19.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.19.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.19.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.19.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.19.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.2.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.2.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.2.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.20.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.20.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.20.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.20.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.20.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.20.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.21.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.21.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.21.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.21.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.21.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.21.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.22.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.22.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.22.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.22.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.22.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.22.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.23.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.23.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.23.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.23.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.23.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.23.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.24.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.24.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.24.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.24.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.24.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.24.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.25.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.25.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.25.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.25.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.25.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.25.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.26.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.26.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.26.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.26.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.26.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.26.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.27.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.27.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.27.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.27.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.27.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.27.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.28.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.28.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.28.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.28.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.28.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.28.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.29.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.29.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.29.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.29.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.29.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.29.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.3.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.3.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.3.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.3.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.3.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.3.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.30.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.30.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.30.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.30.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.30.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.30.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.31.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.31.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.31.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.31.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.31.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.31.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.32.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.32.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.32.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.32.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.32.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.32.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.33.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.33.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.33.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.33.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.33.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.33.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.34.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.34.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.34.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.34.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.34.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.34.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.35.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.35.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.35.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.35.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.35.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.35.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.36.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.36.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.36.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.36.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.36.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.36.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.37.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.37.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.37.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.37.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.37.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.37.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.38.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.38.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.38.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.38.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.38.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.38.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.39.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.39.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.39.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.39.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.39.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.39.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.4.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.4.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.4.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.4.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.4.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.4.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.40.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.40.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.40.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.40.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.40.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.40.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.41.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.41.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.41.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.41.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.41.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.41.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.42.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.42.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.42.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.42.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.42.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.42.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.43.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.43.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.43.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.43.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.43.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.43.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.44.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.44.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.44.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.44.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.44.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.44.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.45.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.45.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.45.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.45.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.45.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.45.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.46.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.46.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.46.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.46.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.46.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.46.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.47.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.47.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.47.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.47.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.47.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.47.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.48.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.48.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.48.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.48.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.48.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.48.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.49.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.49.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.49.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.49.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.49.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.49.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.5.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.5.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.5.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.5.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.5.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.5.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.50.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.50.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.50.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.50.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.50.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.50.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.51.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.51.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.51.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.51.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.51.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.51.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.52.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.52.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.52.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.52.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.52.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.52.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.53.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.53.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.53.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.53.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.53.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.53.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.54.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.54.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.54.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.54.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.54.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.54.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.55.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.55.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.55.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.55.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.55.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.55.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.56.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.56.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.56.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.56.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.56.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.56.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.57.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.57.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.57.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.57.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.57.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.57.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.58.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.58.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.58.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.58.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.58.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.58.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.59.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.59.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.59.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.59.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.59.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.59.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.6.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.6.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.6.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.6.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.6.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.6.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.60.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.60.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.60.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.60.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.60.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.60.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.61.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.61.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.61.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.61.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.61.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.61.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.62.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.62.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.62.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.62.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.62.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.62.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.63.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.63.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.63.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.63.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.63.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.63.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.64.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.64.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.64.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.64.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.64.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.64.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.65.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.65.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.65.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.65.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.65.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.65.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.66.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.66.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.66.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.66.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.66.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.66.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.67.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.67.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.67.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.67.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.67.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.67.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.68.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.68.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.68.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.68.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.68.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.68.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.69.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.69.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.69.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.69.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.69.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.69.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.7.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.7.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.7.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.7.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.7.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.7.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.70.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.70.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.70.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.70.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.70.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.70.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.71.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.71.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.71.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.71.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.71.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.71.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.72.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.72.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.72.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.72.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.72.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.72.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.73.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.73.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.73.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.73.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.73.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.73.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.74.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.74.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.74.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.74.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.74.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.74.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.75.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.75.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.75.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.75.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.75.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.75.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.76.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.76.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.76.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.76.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.76.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.76.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.77.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.77.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.77.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.77.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.77.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.77.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.78.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.78.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.78.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.78.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.78.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.78.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.79.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.79.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.79.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.79.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.79.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.79.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.8.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.8.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.8.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.8.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.8.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.8.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.80.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.80.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.80.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.80.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.80.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.80.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.81.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.81.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.81.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.81.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.81.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.81.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.82.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.82.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.82.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.82.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.82.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.82.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.83.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.83.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.83.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.83.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.83.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.83.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.84.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.84.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.84.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.84.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.84.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.84.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.85.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.85.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.85.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.85.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.85.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.85.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.86.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.86.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.86.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.86.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.86.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.86.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.87.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.87.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.87.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.87.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.87.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.87.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.88.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.88.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.88.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.88.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.88.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.88.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.89.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.89.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.89.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.89.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.89.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.89.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.9.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.9.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.9.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.9.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.9.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.9.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.90.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.90.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.90.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.90.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.90.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.90.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.91.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.91.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.91.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.91.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.91.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.91.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.92.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.92.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.92.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.92.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.92.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.92.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.93.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.93.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.93.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.93.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.93.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.93.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.94.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.94.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.94.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.94.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.94.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.94.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.95.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.95.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.95.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.95.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.95.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.95.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.96.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.96.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.96.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.96.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.96.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.96.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.97.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.97.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.97.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.97.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.97.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.97.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.98.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.98.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.98.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.98.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.98.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.98.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.99.w1.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.99.w1.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.99.w2.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.99.w2.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.99.w3.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.experts.99.w3.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.shared_experts.down_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.shared_experts.gate_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.shared_experts.up_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.input_layernorm.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.post_attention_layernorm.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.index_k_norm.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.index_k_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.index_k_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.index_q_norm.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.index_q_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.index_q_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.k_norm.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.k_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.k_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.o_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.o_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.q_norm.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.q_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.q_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.v_proj.weight": "model-00048-of-00059.safetensors", + "language_model.model.layers.48.self_attn.v_proj.weight_scale": "model-00048-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.gate.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.108.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.108.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.108.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.108.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.108.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.108.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.109.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.109.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.109.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.109.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.109.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.109.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.11.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.11.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.11.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.11.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.11.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.11.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.110.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.110.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.110.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.110.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.110.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.110.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.111.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.111.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.111.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.111.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.111.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.111.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.112.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.112.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.112.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.112.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.112.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.112.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.113.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.113.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.113.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.113.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.113.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.113.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.114.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.114.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.114.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.114.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.114.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.114.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.115.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.115.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.115.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.115.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.115.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.115.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.116.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.116.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.116.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.116.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.116.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.116.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.117.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.117.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.117.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.117.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.117.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.117.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.118.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.118.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.118.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.118.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.118.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.118.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.119.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.119.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.119.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.119.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.119.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.119.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.12.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.12.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.12.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.12.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.12.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.12.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.120.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.120.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.120.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.120.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.120.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.120.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.121.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.121.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.121.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.121.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.121.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.121.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.122.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.122.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.122.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.122.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.122.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.122.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.123.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.123.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.123.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.123.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.123.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.123.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.124.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.124.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.124.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.124.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.124.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.124.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.125.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.125.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.125.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.125.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.125.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.125.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.126.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.126.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.126.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.126.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.126.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.126.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.127.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.127.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.127.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.127.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.127.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.127.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.13.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.13.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.13.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.13.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.13.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.13.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.14.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.14.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.14.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.14.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.14.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.14.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.15.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.15.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.15.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.15.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.15.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.15.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.16.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.16.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.16.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.16.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.16.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.16.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.17.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.17.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.17.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.17.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.17.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.17.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.18.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.18.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.18.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.18.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.18.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.18.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.19.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.19.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.19.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.19.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.19.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.19.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.2.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.2.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.2.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.20.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.20.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.20.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.20.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.20.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.20.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.21.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.21.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.21.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.21.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.21.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.21.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.22.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.22.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.22.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.22.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.22.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.22.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.23.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.23.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.23.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.23.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.23.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.23.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.24.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.24.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.24.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.24.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.24.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.24.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.25.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.25.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.25.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.25.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.25.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.25.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.26.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.26.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.26.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.26.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.26.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.26.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.27.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.27.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.27.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.27.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.27.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.27.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.28.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.28.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.28.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.28.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.28.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.28.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.29.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.29.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.29.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.29.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.29.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.29.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.3.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.3.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.3.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.30.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.30.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.30.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.30.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.30.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.30.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.31.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.31.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.31.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.31.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.31.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.31.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.32.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.32.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.32.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.32.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.32.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.32.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.33.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.33.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.33.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.33.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.33.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.33.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.34.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.34.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.34.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.34.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.34.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.34.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.35.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.35.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.35.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.35.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.35.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.35.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.36.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.36.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.36.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.36.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.36.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.36.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.37.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.37.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.37.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.37.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.37.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.37.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.38.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.38.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.38.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.38.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.38.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.38.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.39.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.39.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.39.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.39.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.39.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.39.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.4.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.4.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.4.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.40.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.40.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.40.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.40.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.40.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.40.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.41.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.41.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.41.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.41.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.41.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.41.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.42.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.42.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.42.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.42.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.42.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.42.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.43.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.43.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.43.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.43.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.43.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.43.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.44.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.44.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.44.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.44.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.44.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.44.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.45.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.45.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.45.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.45.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.45.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.45.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.46.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.46.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.46.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.46.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.46.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.46.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.47.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.47.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.47.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.47.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.47.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.47.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.48.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.48.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.48.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.48.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.48.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.48.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.49.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.49.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.49.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.49.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.49.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.49.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.5.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.5.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.5.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.50.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.50.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.50.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.50.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.50.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.50.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.51.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.51.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.51.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.51.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.51.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.51.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.52.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.52.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.52.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.52.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.52.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.52.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.53.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.53.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.53.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.53.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.53.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.53.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.54.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.54.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.54.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.54.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.54.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.54.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.55.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.55.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.55.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.55.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.55.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.55.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.56.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.56.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.56.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.56.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.56.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.56.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.57.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.57.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.57.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.57.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.57.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.57.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.58.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.58.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.58.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.58.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.58.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.58.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.59.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.59.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.59.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.59.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.59.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.59.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.6.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.6.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.6.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.60.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.60.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.60.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.60.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.60.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.60.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.61.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.61.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.61.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.61.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.61.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.61.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.62.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.62.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.62.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.62.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.62.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.62.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.63.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.63.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.63.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.63.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.63.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.63.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.64.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.64.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.64.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.64.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.64.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.64.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.65.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.65.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.65.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.65.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.65.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.65.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.66.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.66.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.66.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.66.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.66.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.66.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.67.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.67.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.67.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.67.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.67.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.67.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.68.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.68.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.68.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.68.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.68.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.68.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.69.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.69.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.69.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.69.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.69.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.69.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.7.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.7.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.7.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.70.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.70.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.70.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.70.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.70.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.70.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.71.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.71.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.71.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.71.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.71.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.71.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.72.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.72.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.72.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.72.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.72.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.72.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.73.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.73.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.73.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.73.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.73.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.73.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.74.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.74.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.74.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.74.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.74.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.74.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.75.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.75.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.75.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.75.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.75.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.75.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.76.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.76.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.76.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.76.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.76.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.76.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.77.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.77.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.77.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.77.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.77.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.77.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.78.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.78.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.78.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.78.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.78.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.78.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.79.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.79.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.79.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.79.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.79.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.79.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.8.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.8.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.8.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.8.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.8.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.8.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.80.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.80.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.80.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.80.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.80.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.80.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.81.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.81.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.81.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.81.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.81.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.81.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.82.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.82.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.82.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.82.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.82.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.82.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.83.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.83.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.83.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.83.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.83.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.83.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.84.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.84.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.84.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.84.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.84.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.84.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.85.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.85.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.85.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.85.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.85.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.85.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.86.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.86.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.86.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.86.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.86.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.86.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.87.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.87.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.87.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.87.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.87.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.87.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.88.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.88.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.88.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.88.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.88.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.88.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.89.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.89.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.89.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.89.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.89.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.89.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.9.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.9.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.9.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.9.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.9.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.9.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.90.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.90.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.90.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.90.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.90.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.90.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.91.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.91.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.91.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.91.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.91.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.91.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.92.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.92.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.92.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.92.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.92.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.92.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.93.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.93.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.93.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.93.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.93.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.93.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.94.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.94.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.94.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.94.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.94.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.94.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.95.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.95.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.95.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.95.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.95.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.95.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.96.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.96.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.96.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.96.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.96.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.96.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.97.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.97.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.97.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.97.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.97.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.97.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.98.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.98.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.98.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.98.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.98.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.98.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.99.w1.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.99.w1.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.99.w2.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.99.w2.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.99.w3.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.experts.99.w3.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.shared_experts.down_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.shared_experts.gate_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.shared_experts.up_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.input_layernorm.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.post_attention_layernorm.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.index_k_norm.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.index_k_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.index_k_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.index_q_norm.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.index_q_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.index_q_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.k_norm.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.k_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.k_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.o_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.o_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.q_norm.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.q_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.q_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.v_proj.weight": "model-00038-of-00059.safetensors", + "language_model.model.layers.38.self_attn.v_proj.weight_scale": "model-00038-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.e_score_correction_bias": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.gate.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.e_score_correction_bias": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.0.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.0.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.0.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.1.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.1.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.1.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.10.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.10.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.10.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.10.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.10.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.10.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.100.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.100.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.100.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.100.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.100.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.100.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.101.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.101.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.101.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.101.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.101.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.101.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.102.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.102.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.102.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.102.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.102.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.102.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.103.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.103.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.103.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.103.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.103.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.103.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.104.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.104.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.104.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.104.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.104.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.104.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.105.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.105.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.105.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.105.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.105.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.105.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.106.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.106.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.106.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.106.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.106.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.106.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.107.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.107.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.107.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.107.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.107.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.107.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.108.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.108.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.108.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.108.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.108.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.108.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.109.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.109.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.109.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.109.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.109.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.109.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.11.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.11.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.11.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.11.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.11.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.11.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.110.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.110.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.110.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.110.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.110.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.110.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.111.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.111.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.111.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.111.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.111.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.111.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.112.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.112.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.112.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.112.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.112.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.112.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.113.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.113.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.113.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.113.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.113.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.113.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.114.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.114.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.114.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.114.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.114.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.114.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.115.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.115.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.115.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.115.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.115.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.115.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.116.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.116.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.116.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.116.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.116.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.116.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.117.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.117.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.117.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.117.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.117.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.117.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.118.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.118.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.118.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.118.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.118.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.118.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.119.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.119.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.119.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.119.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.119.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.119.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.12.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.12.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.12.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.12.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.12.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.12.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.120.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.120.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.120.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.120.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.120.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.120.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.121.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.121.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.121.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.121.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.121.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.121.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.122.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.122.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.122.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.122.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.122.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.122.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.123.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.123.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.123.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.123.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.123.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.123.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.124.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.124.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.124.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.124.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.124.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.124.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.125.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.125.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.125.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.125.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.125.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.125.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.126.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.126.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.126.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.126.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.126.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.126.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.127.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.127.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.127.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.127.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.127.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.127.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.13.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.13.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.13.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.13.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.13.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.13.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.14.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.14.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.14.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.14.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.14.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.14.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.15.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.15.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.15.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.15.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.15.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.15.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.16.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.16.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.16.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.16.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.16.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.16.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.17.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.17.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.17.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.17.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.17.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.17.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.18.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.18.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.18.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.18.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.18.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.18.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.19.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.19.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.19.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.19.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.19.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.19.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.2.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.2.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.2.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.20.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.20.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.20.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.20.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.20.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.20.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.21.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.21.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.21.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.21.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.21.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.21.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.22.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.22.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.22.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.22.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.22.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.22.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.23.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.23.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.23.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.23.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.23.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.23.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.24.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.24.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.24.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.24.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.24.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.24.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.25.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.25.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.25.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.25.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.25.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.25.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.26.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.26.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.26.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.26.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.26.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.26.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.27.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.27.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.27.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.27.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.27.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.27.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.28.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.28.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.28.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.28.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.28.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.28.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.29.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.29.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.29.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.29.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.29.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.29.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.3.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.3.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.3.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.30.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.30.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.30.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.30.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.30.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.30.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.31.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.31.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.31.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.31.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.31.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.31.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.32.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.32.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.32.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.32.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.32.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.32.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.33.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.33.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.33.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.33.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.33.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.33.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.34.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.34.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.34.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.34.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.34.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.34.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.35.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.35.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.35.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.35.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.35.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.35.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.36.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.36.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.36.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.36.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.36.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.36.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.37.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.37.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.37.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.37.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.37.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.37.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.38.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.38.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.38.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.38.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.38.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.38.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.39.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.39.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.39.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.39.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.39.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.39.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.4.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.4.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.4.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.40.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.40.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.40.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.40.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.40.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.40.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.41.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.41.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.41.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.41.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.41.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.41.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.42.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.42.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.42.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.42.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.42.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.42.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.43.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.43.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.43.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.43.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.43.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.43.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.44.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.44.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.44.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.44.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.44.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.44.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.45.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.45.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.45.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.45.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.45.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.45.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.46.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.46.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.46.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.46.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.46.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.46.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.47.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.47.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.47.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.47.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.47.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.47.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.48.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.48.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.48.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.48.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.48.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.48.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.49.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.49.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.49.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.49.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.49.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.49.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.5.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.5.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.5.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.50.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.50.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.50.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.50.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.50.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.50.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.51.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.51.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.51.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.51.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.51.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.51.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.52.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.52.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.52.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.52.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.52.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.52.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.53.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.53.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.53.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.53.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.53.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.53.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.54.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.54.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.54.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.54.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.54.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.54.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.55.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.55.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.55.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.55.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.55.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.55.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.56.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.56.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.56.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.56.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.56.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.56.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.57.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.57.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.57.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.57.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.57.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.57.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.58.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.58.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.58.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.58.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.58.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.58.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.59.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.59.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.59.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.59.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.59.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.59.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.6.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.6.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.6.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.60.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.60.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.60.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.60.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.60.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.60.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.61.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.61.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.61.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.61.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.61.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.61.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.62.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.62.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.62.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.62.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.62.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.62.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.63.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.63.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.63.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.63.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.63.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.63.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.64.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.64.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.64.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.64.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.64.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.64.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.65.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.65.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.65.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.65.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.65.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.65.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.66.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.66.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.66.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.66.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.66.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.66.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.67.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.67.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.67.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.67.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.67.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.67.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.68.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.68.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.68.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.68.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.68.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.68.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.69.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.69.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.69.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.69.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.69.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.69.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.7.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.7.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.7.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.70.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.70.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.70.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.70.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.70.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.70.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.71.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.71.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.71.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.71.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.71.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.71.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.72.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.72.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.72.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.72.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.72.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.72.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.73.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.73.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.73.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.73.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.73.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.73.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.74.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.74.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.74.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.74.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.74.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.74.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.75.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.75.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.75.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.75.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.75.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.75.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.76.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.76.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.76.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.76.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.76.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.76.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.77.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.77.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.77.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.77.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.77.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.77.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.78.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.78.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.78.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.78.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.78.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.78.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.79.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.79.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.79.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.79.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.79.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.79.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.8.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.8.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.8.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.8.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.8.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.8.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.80.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.80.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.80.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.80.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.80.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.80.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.81.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.81.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.81.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.81.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.81.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.81.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.82.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.82.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.82.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.82.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.82.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.82.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.83.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.83.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.83.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.83.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.83.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.83.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.84.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.84.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.84.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.84.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.84.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.84.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.85.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.85.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.85.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.85.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.85.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.85.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.86.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.86.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.86.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.86.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.86.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.86.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.87.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.87.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.87.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.87.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.87.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.87.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.88.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.88.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.88.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.88.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.88.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.88.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.89.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.89.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.89.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.89.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.89.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.89.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.9.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.9.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.9.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.9.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.9.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.9.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.90.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.90.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.90.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.90.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.90.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.90.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.91.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.91.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.91.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.91.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.91.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.91.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.92.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.92.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.92.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.92.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.92.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.92.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.93.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.93.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.93.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.93.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.93.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.93.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.94.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.94.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.94.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.94.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.94.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.94.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.95.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.95.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.95.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.95.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.95.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.95.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.96.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.96.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.96.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.96.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.96.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.96.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.97.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.97.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.97.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.97.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.97.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.97.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.98.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.98.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.98.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.98.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.98.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.98.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.99.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.99.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.99.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.99.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.99.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.experts.99.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.shared_experts.down_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.shared_experts.gate_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.shared_experts.up_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.index_k_norm.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.index_k_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.index_k_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.index_q_norm.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.index_q_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.index_q_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.k_norm.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.q_norm.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.0.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.0.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.0.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.1.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.1.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.1.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.10.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.10.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.10.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.10.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.10.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.10.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.100.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.100.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.100.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.100.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.100.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.100.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.101.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.101.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.101.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.101.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.101.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.101.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.102.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.102.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.102.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.102.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.102.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.102.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.103.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.103.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.103.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.103.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.103.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.103.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.104.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.104.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.104.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.104.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.104.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.104.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.105.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.105.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.105.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.105.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.105.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.105.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.106.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.106.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.106.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.106.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.106.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.106.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.107.w1.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.107.w1.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.107.w2.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.107.w2.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.107.w3.weight": "model-00020-of-00059.safetensors", + "language_model.model.layers.54.block_sparse_moe.experts.107.w3.weight_scale": "model-00020-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.e_score_correction_bias": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.gate.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.0.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.0.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.0.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.1.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.1.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.1.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.10.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.10.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.10.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.10.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.10.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.10.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.100.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.100.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.100.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.100.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.100.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.100.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.101.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.101.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.101.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.101.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.101.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.101.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.102.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.102.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.102.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.102.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.102.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.102.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.103.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.103.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.103.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.103.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.103.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.103.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.104.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.104.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.104.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.104.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.104.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.104.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.105.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.105.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.105.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.105.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.105.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.105.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.106.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.106.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.106.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.106.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.106.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.106.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.107.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.107.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.107.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.107.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.107.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.107.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.108.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.108.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.108.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.108.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.108.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.108.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.109.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.109.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.109.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.109.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.109.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.109.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.11.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.11.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.11.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.11.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.11.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.11.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.110.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.110.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.110.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.110.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.110.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.110.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.111.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.111.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.111.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.111.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.111.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.111.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.112.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.112.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.112.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.112.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.112.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.112.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.113.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.113.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.113.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.113.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.113.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.113.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.114.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.114.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.114.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.114.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.114.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.114.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.115.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.115.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.115.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.115.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.115.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.115.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.116.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.116.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.116.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.116.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.116.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.116.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.117.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.117.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.117.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.117.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.117.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.117.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.118.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.118.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.118.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.118.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.118.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.118.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.119.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.119.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.119.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.119.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.119.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.119.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.12.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.12.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.12.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.12.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.12.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.12.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.120.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.120.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.120.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.120.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.120.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.120.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.121.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.121.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.121.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.121.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.121.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.121.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.122.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.122.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.122.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.122.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.122.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.122.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.123.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.123.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.123.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.123.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.123.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.123.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.124.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.124.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.124.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.124.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.124.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.124.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.125.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.125.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.125.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.125.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.125.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.125.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.126.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.126.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.126.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.126.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.126.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.126.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.127.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.127.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.127.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.127.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.127.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.127.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.13.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.13.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.13.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.13.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.13.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.13.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.14.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.14.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.14.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.14.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.14.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.14.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.15.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.15.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.15.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.15.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.15.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.15.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.16.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.16.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.16.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.16.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.16.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.16.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.17.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.17.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.17.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.17.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.17.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.17.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.18.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.18.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.18.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.18.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.18.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.18.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.19.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.19.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.19.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.19.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.19.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.19.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.2.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.2.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.2.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.20.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.20.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.20.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.20.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.20.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.20.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.21.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.21.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.21.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.21.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.21.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.21.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.22.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.22.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.22.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.22.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.22.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.22.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.23.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.23.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.23.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.23.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.23.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.23.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.24.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.24.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.24.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.24.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.24.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.24.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.25.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.25.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.25.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.25.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.25.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.25.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.26.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.26.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.26.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.26.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.26.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.26.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.27.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.27.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.27.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.27.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.27.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.27.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.28.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.28.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.28.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.28.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.28.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.28.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.29.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.29.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.29.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.29.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.29.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.29.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.3.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.3.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.3.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.30.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.30.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.30.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.30.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.30.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.30.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.31.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.31.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.31.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.31.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.31.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.31.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.32.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.32.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.32.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.32.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.32.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.32.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.33.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.33.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.33.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.33.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.33.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.33.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.34.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.34.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.34.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.34.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.34.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.34.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.35.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.35.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.35.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.35.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.35.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.35.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.36.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.36.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.36.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.36.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.36.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.36.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.37.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.37.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.37.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.37.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.37.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.37.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.38.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.38.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.38.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.38.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.38.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.38.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.39.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.39.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.39.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.39.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.39.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.39.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.4.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.4.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.4.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.40.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.40.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.40.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.40.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.40.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.40.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.41.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.41.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.41.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.41.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.41.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.41.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.42.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.42.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.42.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.42.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.42.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.42.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.43.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.43.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.43.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.43.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.43.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.43.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.44.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.44.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.44.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.44.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.44.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.44.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.45.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.45.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.45.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.45.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.45.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.45.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.46.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.46.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.46.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.46.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.46.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.46.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.47.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.47.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.47.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.47.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.47.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.47.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.48.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.48.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.48.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.48.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.48.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.48.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.49.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.49.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.49.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.49.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.49.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.49.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.5.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.5.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.5.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.50.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.50.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.50.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.50.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.50.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.50.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.51.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.51.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.51.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.51.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.51.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.51.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.52.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.52.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.52.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.52.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.52.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.52.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.53.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.53.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.53.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.53.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.53.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.53.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.54.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.54.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.54.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.54.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.54.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.54.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.55.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.55.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.55.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.55.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.55.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.55.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.56.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.56.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.56.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.56.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.56.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.56.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.57.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.57.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.57.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.57.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.57.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.57.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.58.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.58.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.58.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.58.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.58.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.58.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.59.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.59.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.59.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.59.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.59.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.59.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.6.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.6.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.6.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.60.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.60.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.60.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.60.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.60.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.60.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.61.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.61.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.61.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.61.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.61.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.61.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.62.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.62.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.62.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.62.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.62.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.62.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.63.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.63.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.63.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.63.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.63.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.63.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.64.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.64.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.64.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.64.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.64.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.64.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.65.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.65.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.65.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.65.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.65.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.65.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.66.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.66.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.66.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.66.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.66.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.66.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.67.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.67.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.67.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.67.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.67.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.67.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.68.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.68.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.68.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.68.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.68.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.68.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.69.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.69.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.69.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.69.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.69.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.69.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.7.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.7.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.7.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.70.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.70.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.70.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.70.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.70.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.70.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.71.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.71.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.71.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.71.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.71.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.71.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.72.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.72.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.72.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.72.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.72.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.72.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.73.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.73.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.73.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.73.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.73.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.73.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.74.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.74.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.74.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.74.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.74.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.74.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.75.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.75.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.75.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.75.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.75.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.75.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.76.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.76.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.76.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.76.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.76.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.76.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.77.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.77.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.77.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.77.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.77.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.77.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.78.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.78.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.78.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.78.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.78.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.78.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.79.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.79.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.79.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.79.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.79.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.79.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.8.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.8.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.8.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.8.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.8.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.8.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.80.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.80.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.80.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.80.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.80.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.80.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.81.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.81.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.81.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.81.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.81.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.81.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.82.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.82.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.82.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.82.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.82.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.82.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.83.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.83.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.83.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.83.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.83.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.83.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.84.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.84.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.84.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.84.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.84.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.84.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.85.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.85.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.85.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.85.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.85.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.85.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.86.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.86.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.86.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.86.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.86.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.86.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.87.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.87.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.87.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.87.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.87.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.87.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.88.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.88.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.88.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.88.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.88.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.88.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.89.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.89.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.89.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.89.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.89.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.89.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.9.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.9.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.9.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.9.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.9.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.9.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.90.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.90.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.90.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.90.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.90.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.90.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.91.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.91.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.91.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.91.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.91.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.91.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.92.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.92.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.92.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.92.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.92.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.92.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.93.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.93.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.93.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.93.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.93.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.93.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.94.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.94.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.94.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.94.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.94.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.94.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.95.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.95.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.95.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.95.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.95.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.95.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.96.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.96.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.96.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.96.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.96.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.96.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.97.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.97.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.97.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.97.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.97.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.97.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.98.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.98.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.98.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.98.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.98.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.98.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.99.w1.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.99.w1.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.99.w2.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.99.w2.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.99.w3.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.experts.99.w3.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.shared_experts.down_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.shared_experts.gate_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.shared_experts.up_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.input_layernorm.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.post_attention_layernorm.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.index_k_norm.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.index_k_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.index_k_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.index_q_norm.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.index_q_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.index_q_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.k_norm.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.k_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.k_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.o_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.o_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.q_norm.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.q_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.q_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.v_proj.weight": "model-00032-of-00059.safetensors", + "language_model.model.layers.32.self_attn.v_proj.weight_scale": "model-00032-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.e_score_correction_bias": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.gate.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.0.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.0.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.0.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.1.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.1.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.1.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.10.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.10.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.10.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.10.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.10.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.10.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.100.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.100.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.100.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.100.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.100.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.100.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.101.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.101.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.101.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.101.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.101.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.101.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.102.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.102.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.102.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.102.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.102.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.102.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.103.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.103.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.103.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.103.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.103.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.103.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.104.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.104.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.104.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.104.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.104.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.104.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.105.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.105.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.105.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.105.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.105.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.105.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.106.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.106.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.106.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.106.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.106.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.106.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.107.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.107.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.107.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.107.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.107.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.107.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.108.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.108.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.108.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.108.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.108.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.108.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.109.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.109.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.109.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.109.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.109.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.109.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.11.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.11.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.11.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.11.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.11.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.11.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.110.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.110.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.110.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.110.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.110.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.110.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.111.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.111.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.111.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.111.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.111.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.111.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.112.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.112.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.112.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.112.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.112.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.112.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.113.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.113.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.113.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.113.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.113.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.113.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.114.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.114.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.114.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.114.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.114.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.114.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.115.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.115.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.115.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.115.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.115.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.115.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.116.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.116.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.116.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.116.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.116.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.116.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.117.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.117.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.117.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.117.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.117.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.117.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.118.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.118.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.118.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.118.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.118.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.118.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.119.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.119.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.119.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.119.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.119.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.119.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.12.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.12.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.12.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.12.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.12.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.12.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.120.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.120.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.120.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.120.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.120.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.120.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.121.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.121.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.121.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.121.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.121.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.121.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.122.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.122.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.122.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.122.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.122.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.122.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.123.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.123.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.123.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.123.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.123.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.123.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.124.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.124.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.124.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.124.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.124.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.124.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.125.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.125.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.125.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.125.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.125.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.125.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.126.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.126.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.126.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.126.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.126.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.126.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.127.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.127.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.127.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.127.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.127.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.127.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.13.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.13.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.13.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.13.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.13.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.13.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.14.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.14.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.14.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.14.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.14.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.14.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.15.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.15.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.15.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.15.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.15.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.15.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.16.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.16.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.16.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.16.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.16.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.16.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.17.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.17.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.17.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.17.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.17.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.17.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.18.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.18.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.18.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.18.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.18.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.18.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.19.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.19.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.19.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.19.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.19.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.19.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.2.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.2.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.2.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.20.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.20.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.20.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.20.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.20.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.20.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.21.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.21.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.21.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.21.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.21.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.21.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.22.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.22.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.22.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.22.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.22.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.22.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.23.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.23.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.23.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.23.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.23.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.23.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.24.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.24.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.24.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.24.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.24.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.24.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.25.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.25.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.25.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.25.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.25.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.25.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.26.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.26.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.26.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.26.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.26.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.26.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.27.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.27.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.27.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.27.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.27.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.27.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.28.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.28.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.28.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.28.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.28.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.28.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.29.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.29.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.29.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.29.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.29.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.29.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.3.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.3.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.3.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.30.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.30.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.30.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.30.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.30.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.30.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.31.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.31.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.31.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.31.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.31.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.31.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.32.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.32.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.32.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.32.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.32.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.32.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.33.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.33.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.33.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.33.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.33.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.33.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.34.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.34.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.34.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.34.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.34.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.34.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.35.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.35.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.35.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.35.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.35.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.35.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.36.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.36.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.36.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.36.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.36.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.36.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.37.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.37.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.37.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.37.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.37.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.37.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.38.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.38.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.38.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.38.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.38.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.38.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.39.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.39.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.39.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.39.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.39.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.39.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.4.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.4.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.4.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.40.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.40.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.40.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.40.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.40.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.40.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.41.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.41.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.41.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.41.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.41.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.41.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.42.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.42.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.42.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.42.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.42.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.42.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.43.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.43.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.43.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.43.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.43.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.43.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.44.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.44.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.44.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.44.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.44.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.44.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.45.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.45.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.45.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.45.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.45.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.45.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.46.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.46.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.46.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.46.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.46.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.46.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.47.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.47.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.47.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.47.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.47.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.47.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.48.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.48.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.48.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.48.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.48.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.48.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.49.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.49.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.49.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.49.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.49.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.49.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.5.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.5.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.5.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.50.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.50.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.50.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.50.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.50.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.50.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.51.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.51.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.51.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.51.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.51.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.51.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.52.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.52.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.52.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.52.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.52.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.52.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.53.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.53.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.53.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.53.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.53.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.53.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.54.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.54.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.54.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.54.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.54.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.54.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.55.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.55.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.55.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.55.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.55.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.55.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.56.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.56.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.56.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.56.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.56.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.56.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.57.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.57.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.57.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.57.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.57.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.57.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.58.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.58.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.58.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.58.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.58.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.58.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.59.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.59.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.59.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.59.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.59.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.59.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.6.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.6.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.6.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.60.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.60.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.60.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.60.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.60.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.60.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.61.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.61.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.61.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.61.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.61.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.61.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.62.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.62.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.62.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.62.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.62.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.62.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.63.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.63.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.63.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.63.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.63.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.63.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.64.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.64.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.64.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.64.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.64.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.64.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.65.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.65.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.65.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.65.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.65.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.65.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.66.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.66.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.66.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.66.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.66.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.66.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.67.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.67.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.67.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.67.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.67.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.67.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.68.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.68.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.68.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.68.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.68.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.68.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.69.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.69.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.69.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.69.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.69.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.69.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.7.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.7.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.7.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.70.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.70.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.70.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.70.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.70.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.70.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.71.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.71.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.71.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.71.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.71.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.71.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.72.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.72.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.72.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.72.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.72.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.72.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.73.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.73.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.73.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.73.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.73.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.73.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.74.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.74.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.74.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.74.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.74.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.74.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.75.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.75.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.75.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.75.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.75.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.75.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.76.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.76.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.76.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.76.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.76.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.76.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.77.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.77.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.77.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.77.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.77.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.77.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.78.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.78.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.78.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.78.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.78.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.78.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.79.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.79.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.79.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.79.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.79.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.79.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.8.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.8.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.8.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.8.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.8.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.8.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.80.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.80.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.80.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.80.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.80.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.80.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.81.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.81.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.81.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.81.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.81.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.81.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.82.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.82.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.82.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.82.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.82.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.82.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.83.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.83.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.83.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.83.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.83.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.83.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.84.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.84.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.84.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.84.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.84.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.84.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.85.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.85.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.85.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.85.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.85.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.85.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.86.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.86.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.86.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.86.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.86.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.86.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.87.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.87.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.87.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.87.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.87.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.87.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.88.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.88.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.88.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.88.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.88.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.88.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.89.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.89.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.89.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.89.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.89.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.89.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.9.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.9.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.9.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.9.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.9.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.9.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.90.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.90.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.90.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.90.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.90.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.90.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.91.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.91.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.91.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.91.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.91.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.91.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.92.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.92.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.92.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.92.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.92.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.92.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.93.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.93.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.93.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.93.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.93.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.93.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.94.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.94.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.94.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.94.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.94.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.94.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.95.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.95.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.95.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.95.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.95.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.95.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.96.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.96.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.96.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.96.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.96.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.96.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.97.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.97.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.97.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.97.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.97.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.97.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.98.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.98.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.98.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.98.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.98.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.98.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.99.w1.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.99.w1.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.99.w2.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.99.w2.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.99.w3.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.experts.99.w3.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.shared_experts.down_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.shared_experts.gate_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.shared_experts.up_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.input_layernorm.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.post_attention_layernorm.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.index_k_norm.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.index_k_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.index_k_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.index_q_norm.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.index_q_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.index_q_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.k_norm.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.k_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.k_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.o_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.o_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.q_norm.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.q_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.q_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.v_proj.weight": "model-00034-of-00059.safetensors", + "language_model.model.layers.34.self_attn.v_proj.weight_scale": "model-00034-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.gate.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.108.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.108.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.108.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.108.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.108.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.108.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.109.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.109.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.109.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.109.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.109.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.109.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.11.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.11.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.11.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.11.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.11.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.11.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.110.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.110.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.110.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.110.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.110.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.110.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.111.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.111.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.111.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.111.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.111.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.111.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.112.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.112.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.112.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.112.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.112.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.112.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.113.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.113.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.113.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.113.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.113.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.113.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.114.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.114.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.114.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.114.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.114.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.114.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.115.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.115.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.115.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.115.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.115.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.115.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.116.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.116.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.116.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.116.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.116.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.116.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.117.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.117.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.117.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.117.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.117.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.117.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.118.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.118.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.118.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.118.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.118.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.118.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.119.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.119.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.119.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.119.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.119.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.119.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.12.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.12.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.12.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.12.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.12.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.12.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.120.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.120.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.120.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.120.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.120.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.120.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.121.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.121.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.121.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.121.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.121.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.121.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.122.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.122.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.122.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.122.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.122.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.122.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.123.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.123.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.123.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.123.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.123.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.123.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.124.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.124.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.124.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.124.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.124.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.124.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.125.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.125.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.125.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.125.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.125.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.125.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.126.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.126.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.126.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.126.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.126.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.126.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.127.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.127.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.127.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.127.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.127.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.127.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.13.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.13.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.13.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.13.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.13.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.13.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.14.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.14.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.14.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.14.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.14.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.14.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.15.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.15.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.15.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.15.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.15.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.15.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.16.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.16.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.16.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.16.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.16.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.16.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.17.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.17.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.17.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.17.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.17.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.17.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.18.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.18.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.18.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.18.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.18.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.18.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.19.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.19.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.19.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.19.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.19.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.19.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.2.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.2.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.2.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.20.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.20.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.20.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.20.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.20.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.20.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.21.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.21.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.21.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.21.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.21.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.21.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.22.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.22.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.22.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.22.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.22.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.22.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.23.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.23.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.23.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.23.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.23.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.23.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.24.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.24.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.24.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.24.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.24.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.24.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.25.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.25.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.25.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.25.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.25.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.25.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.26.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.26.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.26.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.26.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.26.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.26.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.27.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.27.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.27.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.27.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.27.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.27.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.28.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.28.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.28.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.28.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.28.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.28.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.29.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.29.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.29.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.29.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.29.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.29.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.3.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.3.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.3.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.30.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.30.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.30.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.30.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.30.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.30.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.31.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.31.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.31.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.31.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.31.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.31.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.32.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.32.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.32.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.32.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.32.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.32.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.33.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.33.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.33.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.33.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.33.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.33.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.34.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.34.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.34.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.34.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.34.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.34.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.35.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.35.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.35.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.35.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.35.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.35.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.36.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.36.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.36.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.36.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.36.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.36.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.37.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.37.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.37.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.37.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.37.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.37.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.38.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.38.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.38.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.38.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.38.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.38.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.39.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.39.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.39.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.39.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.39.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.39.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.4.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.4.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.4.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.4.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.4.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.4.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.40.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.40.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.40.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.40.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.40.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.40.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.41.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.41.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.41.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.41.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.41.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.41.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.42.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.42.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.42.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.42.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.42.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.42.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.43.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.43.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.43.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.43.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.43.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.43.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.44.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.44.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.44.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.44.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.44.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.44.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.45.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.45.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.45.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.45.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.45.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.45.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.46.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.46.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.46.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.46.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.46.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.46.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.47.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.47.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.47.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.47.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.47.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.47.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.48.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.48.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.48.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.48.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.48.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.48.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.49.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.49.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.49.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.49.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.49.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.49.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.5.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.5.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.5.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.5.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.5.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.5.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.50.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.50.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.50.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.50.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.50.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.50.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.51.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.51.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.51.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.51.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.51.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.51.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.52.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.52.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.52.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.52.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.52.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.52.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.53.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.53.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.53.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.53.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.53.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.53.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.54.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.54.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.54.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.54.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.54.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.54.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.55.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.55.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.55.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.55.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.55.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.55.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.56.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.56.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.56.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.56.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.56.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.56.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.57.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.57.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.57.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.57.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.57.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.57.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.58.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.58.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.58.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.58.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.58.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.58.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.59.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.59.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.59.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.59.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.59.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.59.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.6.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.6.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.6.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.6.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.6.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.6.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.60.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.60.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.60.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.60.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.60.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.60.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.61.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.61.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.61.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.61.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.61.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.61.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.62.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.62.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.62.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.62.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.62.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.62.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.63.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.63.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.63.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.63.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.63.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.63.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.64.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.64.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.64.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.64.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.64.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.64.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.65.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.65.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.65.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.65.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.65.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.65.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.66.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.66.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.66.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.66.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.66.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.66.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.67.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.67.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.67.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.67.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.67.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.67.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.68.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.68.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.68.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.68.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.68.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.68.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.69.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.69.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.69.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.69.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.69.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.69.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.7.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.7.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.7.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.7.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.7.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.7.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.70.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.70.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.70.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.70.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.70.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.70.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.71.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.71.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.71.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.71.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.71.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.71.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.72.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.72.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.72.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.72.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.72.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.72.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.73.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.73.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.73.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.73.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.73.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.73.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.74.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.74.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.74.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.74.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.74.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.74.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.75.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.75.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.75.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.75.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.75.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.75.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.76.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.76.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.76.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.76.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.76.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.76.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.77.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.77.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.77.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.77.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.77.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.77.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.78.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.78.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.78.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.78.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.78.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.78.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.79.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.79.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.79.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.79.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.79.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.79.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.8.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.8.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.8.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.8.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.8.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.8.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.80.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.80.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.80.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.80.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.80.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.80.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.81.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.81.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.81.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.81.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.81.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.81.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.82.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.82.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.82.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.82.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.82.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.82.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.83.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.83.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.83.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.83.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.83.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.83.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.84.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.84.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.84.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.84.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.84.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.84.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.85.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.85.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.85.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.85.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.85.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.85.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.86.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.86.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.86.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.86.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.86.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.86.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.87.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.87.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.87.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.87.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.87.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.87.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.88.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.88.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.88.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.88.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.88.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.88.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.89.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.89.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.89.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.89.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.89.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.89.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.9.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.9.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.9.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.9.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.9.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.9.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.90.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.90.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.90.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.90.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.90.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.90.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.91.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.91.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.91.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.91.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.91.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.91.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.92.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.92.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.92.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.92.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.92.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.92.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.93.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.93.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.93.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.93.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.93.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.93.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.94.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.94.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.94.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.94.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.94.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.94.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.95.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.95.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.95.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.95.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.95.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.95.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.96.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.96.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.96.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.96.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.96.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.96.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.97.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.97.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.97.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.97.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.97.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.97.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.98.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.98.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.98.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.98.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.98.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.98.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.99.w1.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.99.w1.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.99.w2.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.99.w2.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.99.w3.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.experts.99.w3.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.shared_experts.down_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.shared_experts.gate_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.shared_experts.up_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.input_layernorm.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.post_attention_layernorm.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.index_k_norm.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.index_k_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.index_k_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.index_q_norm.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.index_q_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.index_q_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.k_norm.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.k_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.k_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.o_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.o_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.q_norm.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.q_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.q_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.v_proj.weight": "model-00044-of-00059.safetensors", + "language_model.model.layers.44.self_attn.v_proj.weight_scale": "model-00044-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.e_score_correction_bias": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.e_score_correction_bias": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.0.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.0.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.0.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.1.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.1.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.1.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.10.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.10.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.10.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.100.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.100.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.100.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.101.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.101.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.101.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.102.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.102.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.102.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.103.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.103.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.103.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.104.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.104.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.104.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.105.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.105.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.105.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.106.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.106.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.106.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.107.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.107.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.107.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.108.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.108.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.108.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.108.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.108.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.108.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.109.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.109.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.109.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.109.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.109.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.109.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.11.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.11.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.11.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.110.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.110.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.110.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.110.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.110.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.110.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.111.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.111.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.111.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.111.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.111.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.111.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.112.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.112.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.112.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.112.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.112.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.112.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.113.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.113.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.113.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.113.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.113.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.113.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.114.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.114.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.114.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.114.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.114.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.114.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.115.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.115.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.115.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.115.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.115.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.115.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.116.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.116.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.116.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.116.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.116.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.116.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.117.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.117.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.117.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.117.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.117.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.117.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.118.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.118.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.118.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.118.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.118.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.118.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.119.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.119.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.119.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.119.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.119.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.119.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.12.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.12.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.12.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.120.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.120.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.120.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.120.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.120.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.120.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.121.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.121.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.121.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.121.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.121.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.121.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.122.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.122.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.122.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.122.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.122.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.122.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.123.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.123.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.123.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.123.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.123.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.123.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.124.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.124.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.124.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.124.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.124.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.124.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.125.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.125.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.125.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.125.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.125.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.125.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.126.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.126.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.126.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.126.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.126.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.126.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.127.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.127.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.127.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.127.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.127.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.127.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.13.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.13.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.13.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.14.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.14.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.14.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.15.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.15.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.15.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.16.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.16.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.16.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.17.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.17.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.17.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.18.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.18.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.18.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.19.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.19.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.19.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.2.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.2.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.2.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.20.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.20.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.20.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.21.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.21.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.21.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.22.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.22.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.22.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.23.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.23.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.23.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.24.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.24.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.24.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.25.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.25.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.25.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.26.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.26.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.26.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.27.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.27.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.27.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.28.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.28.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.28.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.29.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.29.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.29.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.3.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.3.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.3.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.30.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.30.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.30.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.31.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.31.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.31.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.32.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.32.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.32.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.32.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.32.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.32.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.33.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.33.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.33.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.33.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.33.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.33.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.34.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.34.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.34.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.34.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.34.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.34.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.35.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.35.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.35.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.35.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.35.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.35.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.36.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.36.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.36.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.36.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.36.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.36.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.37.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.37.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.37.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.37.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.37.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.37.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.38.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.38.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.38.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.38.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.38.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.38.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.39.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.39.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.39.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.39.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.39.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.39.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.4.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.4.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.4.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.40.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.40.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.40.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.40.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.40.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.40.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.41.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.41.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.41.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.41.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.41.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.41.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.42.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.42.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.42.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.42.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.42.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.42.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.43.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.43.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.43.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.43.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.43.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.43.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.44.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.44.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.44.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.44.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.44.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.44.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.45.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.45.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.45.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.45.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.45.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.45.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.46.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.46.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.46.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.46.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.46.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.46.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.47.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.47.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.47.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.47.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.47.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.47.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.48.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.48.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.48.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.48.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.48.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.48.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.49.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.49.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.49.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.49.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.49.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.49.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.5.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.5.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.5.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.50.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.50.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.50.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.50.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.50.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.50.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.51.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.51.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.51.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.51.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.51.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.51.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.52.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.52.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.52.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.52.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.52.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.52.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.53.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.53.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.53.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.53.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.53.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.53.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.54.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.54.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.54.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.54.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.54.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.54.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.55.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.55.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.55.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.55.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.55.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.55.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.56.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.56.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.56.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.56.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.56.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.56.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.57.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.57.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.57.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.57.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.57.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.57.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.58.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.58.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.58.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.58.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.58.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.58.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.59.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.59.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.59.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.59.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.59.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.59.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.6.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.6.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.6.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.60.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.60.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.60.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.60.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.60.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.60.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.61.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.61.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.61.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.61.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.61.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.61.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.62.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.62.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.62.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.62.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.62.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.62.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.63.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.63.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.63.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.63.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.63.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.63.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.64.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.64.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.64.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.64.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.64.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.64.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.65.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.65.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.65.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.65.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.65.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.65.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.66.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.66.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.66.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.66.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.66.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.66.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.67.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.67.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.67.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.67.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.67.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.67.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.68.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.68.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.68.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.68.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.68.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.68.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.69.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.69.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.69.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.69.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.69.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.69.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.7.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.7.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.7.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.70.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.70.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.70.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.70.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.70.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.70.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.71.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.71.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.71.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.71.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.71.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.71.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.72.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.72.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.72.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.72.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.72.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.72.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.73.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.73.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.73.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.73.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.73.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.73.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.74.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.74.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.74.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.74.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.74.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.74.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.75.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.75.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.75.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.75.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.75.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.75.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.76.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.76.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.76.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.76.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.76.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.76.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.77.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.77.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.77.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.77.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.77.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.77.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.78.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.78.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.78.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.78.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.78.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.78.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.79.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.79.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.79.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.79.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.79.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.79.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.8.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.8.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.8.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.80.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.80.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.80.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.80.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.80.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.80.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.81.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.81.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.81.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.81.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.81.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.81.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.82.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.82.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.82.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.82.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.82.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.82.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.83.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.83.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.83.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.83.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.83.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.83.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.84.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.84.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.84.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.84.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.84.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.84.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.85.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.85.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.85.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.85.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.85.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.85.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.86.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.86.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.86.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.86.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.86.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.86.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.87.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.87.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.87.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.87.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.87.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.87.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.88.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.88.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.88.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.88.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.88.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.88.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.89.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.89.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.89.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.89.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.89.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.89.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.9.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.9.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.9.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.90.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.90.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.90.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.90.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.90.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.90.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.91.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.91.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.91.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.91.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.91.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.91.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.92.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.92.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.92.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.92.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.92.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.92.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.93.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.93.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.93.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.93.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.93.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.93.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.94.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.94.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.94.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.94.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.94.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.94.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.95.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.95.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.95.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.95.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.95.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.95.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.96.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.96.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.96.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.96.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.96.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.96.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.97.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.97.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.97.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.97.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.97.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.97.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.98.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.98.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.98.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.98.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.98.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.98.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.99.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.99.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.99.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.99.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.99.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.experts.99.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.shared_experts.down_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.shared_experts.gate_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.shared_experts.up_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.index_k_norm.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.index_k_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.index_k_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.index_q_norm.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.index_q_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.index_q_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.k_norm.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.q_norm.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.0.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.0.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.0.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.1.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.1.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.1.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.10.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.10.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.10.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.100.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.100.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.100.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.101.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.101.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.101.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.102.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.102.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.102.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.103.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.103.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.103.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.104.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.104.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.104.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.105.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.105.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.105.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.106.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.106.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.106.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.107.w1.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.107.w2.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.107.w3.weight_scale": "model-00012-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.gate.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.108.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.108.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.108.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.108.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.108.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.108.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.109.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.109.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.109.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.109.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.109.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.109.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.11.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.11.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.11.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.11.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.11.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.11.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.110.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.110.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.110.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.110.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.110.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.110.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.111.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.111.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.111.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.111.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.111.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.111.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.112.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.112.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.112.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.112.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.112.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.112.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.113.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.113.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.113.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.113.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.113.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.113.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.114.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.114.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.114.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.114.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.114.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.114.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.115.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.115.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.115.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.115.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.115.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.115.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.116.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.116.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.116.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.116.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.116.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.116.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.117.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.117.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.117.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.117.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.117.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.117.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.118.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.118.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.118.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.118.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.118.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.118.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.119.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.119.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.119.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.119.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.119.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.119.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.12.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.12.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.12.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.12.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.12.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.12.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.120.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.120.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.120.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.120.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.120.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.120.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.121.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.121.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.121.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.121.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.121.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.121.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.122.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.122.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.122.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.122.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.122.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.122.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.123.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.123.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.123.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.123.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.123.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.123.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.124.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.124.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.124.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.124.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.124.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.124.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.125.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.125.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.125.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.125.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.125.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.125.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.126.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.126.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.126.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.126.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.126.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.126.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.127.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.127.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.127.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.127.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.127.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.127.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.13.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.13.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.13.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.13.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.13.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.13.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.14.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.14.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.14.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.14.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.14.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.14.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.15.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.15.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.15.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.15.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.15.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.15.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.16.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.16.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.16.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.16.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.16.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.16.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.17.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.17.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.17.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.17.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.17.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.17.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.18.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.18.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.18.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.18.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.18.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.18.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.19.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.19.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.19.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.19.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.19.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.19.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.2.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.2.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.2.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.20.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.20.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.20.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.20.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.20.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.20.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.21.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.21.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.21.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.21.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.21.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.21.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.22.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.22.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.22.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.22.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.22.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.22.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.23.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.23.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.23.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.23.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.23.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.23.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.24.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.24.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.24.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.24.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.24.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.24.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.25.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.25.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.25.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.25.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.25.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.25.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.26.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.26.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.26.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.26.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.26.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.26.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.27.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.27.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.27.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.27.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.27.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.27.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.28.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.28.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.28.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.28.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.28.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.28.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.29.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.29.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.29.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.29.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.29.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.29.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.3.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.3.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.3.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.30.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.30.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.30.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.30.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.30.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.30.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.31.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.31.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.31.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.31.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.31.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.31.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.32.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.32.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.32.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.32.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.32.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.32.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.33.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.33.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.33.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.33.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.33.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.33.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.34.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.34.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.34.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.34.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.34.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.34.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.35.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.35.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.35.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.35.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.35.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.35.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.36.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.36.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.36.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.36.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.36.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.36.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.37.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.37.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.37.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.37.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.37.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.37.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.38.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.38.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.38.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.38.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.38.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.38.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.39.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.39.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.39.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.39.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.39.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.39.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.4.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.4.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.4.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.4.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.4.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.4.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.40.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.40.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.40.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.40.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.40.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.40.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.41.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.41.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.41.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.41.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.41.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.41.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.42.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.42.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.42.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.42.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.42.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.42.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.43.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.43.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.43.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.43.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.43.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.43.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.44.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.44.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.44.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.44.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.44.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.44.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.45.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.45.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.45.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.45.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.45.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.45.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.46.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.46.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.46.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.46.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.46.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.46.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.47.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.47.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.47.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.47.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.47.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.47.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.48.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.48.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.48.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.48.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.48.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.48.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.49.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.49.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.49.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.49.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.49.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.49.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.5.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.5.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.5.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.5.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.5.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.5.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.50.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.50.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.50.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.50.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.50.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.50.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.51.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.51.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.51.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.51.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.51.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.51.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.52.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.52.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.52.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.52.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.52.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.52.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.53.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.53.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.53.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.53.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.53.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.53.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.54.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.54.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.54.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.54.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.54.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.54.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.55.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.55.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.55.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.55.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.55.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.55.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.56.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.56.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.56.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.56.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.56.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.56.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.57.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.57.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.57.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.57.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.57.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.57.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.58.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.58.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.58.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.58.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.58.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.58.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.59.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.59.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.59.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.59.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.59.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.59.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.6.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.6.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.6.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.6.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.6.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.6.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.60.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.60.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.60.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.60.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.60.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.60.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.61.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.61.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.61.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.61.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.61.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.61.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.62.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.62.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.62.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.62.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.62.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.62.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.63.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.63.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.63.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.63.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.63.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.63.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.64.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.64.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.64.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.64.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.64.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.64.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.65.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.65.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.65.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.65.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.65.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.65.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.66.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.66.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.66.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.66.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.66.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.66.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.67.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.67.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.67.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.67.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.67.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.67.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.68.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.68.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.68.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.68.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.68.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.68.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.69.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.69.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.69.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.69.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.69.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.69.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.7.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.7.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.7.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.7.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.7.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.7.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.70.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.70.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.70.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.70.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.70.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.70.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.71.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.71.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.71.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.71.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.71.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.71.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.72.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.72.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.72.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.72.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.72.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.72.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.73.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.73.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.73.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.73.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.73.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.73.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.74.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.74.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.74.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.74.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.74.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.74.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.75.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.75.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.75.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.75.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.75.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.75.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.76.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.76.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.76.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.76.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.76.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.76.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.77.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.77.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.77.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.77.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.77.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.77.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.78.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.78.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.78.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.78.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.78.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.78.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.79.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.79.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.79.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.79.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.79.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.79.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.8.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.8.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.8.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.8.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.8.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.8.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.80.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.80.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.80.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.80.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.80.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.80.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.81.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.81.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.81.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.81.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.81.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.81.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.82.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.82.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.82.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.82.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.82.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.82.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.83.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.83.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.83.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.83.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.83.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.83.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.84.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.84.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.84.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.84.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.84.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.84.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.85.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.85.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.85.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.85.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.85.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.85.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.86.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.86.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.86.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.86.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.86.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.86.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.87.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.87.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.87.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.87.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.87.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.87.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.88.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.88.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.88.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.88.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.88.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.88.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.89.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.89.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.89.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.89.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.89.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.89.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.9.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.9.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.9.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.9.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.9.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.9.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.90.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.90.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.90.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.90.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.90.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.90.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.91.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.91.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.91.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.91.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.91.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.91.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.92.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.92.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.92.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.92.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.92.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.92.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.93.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.93.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.93.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.93.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.93.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.93.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.94.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.94.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.94.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.94.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.94.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.94.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.95.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.95.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.95.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.95.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.95.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.95.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.96.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.96.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.96.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.96.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.96.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.96.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.97.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.97.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.97.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.97.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.97.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.97.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.98.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.98.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.98.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.98.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.98.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.98.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.99.w1.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.99.w1.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.99.w2.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.99.w2.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.99.w3.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.experts.99.w3.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.shared_experts.down_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.shared_experts.gate_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.shared_experts.up_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.input_layernorm.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.post_attention_layernorm.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.index_k_norm.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.index_k_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.index_k_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.index_q_norm.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.index_q_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.index_q_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.k_norm.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.k_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.k_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.o_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.o_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.q_norm.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.q_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.q_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.v_proj.weight": "model-00047-of-00059.safetensors", + "language_model.model.layers.47.self_attn.v_proj.weight_scale": "model-00047-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.e_score_correction_bias": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.gate.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.0.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.0.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.0.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.1.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.1.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.1.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.10.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.10.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.10.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.10.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.10.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.10.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.100.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.100.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.100.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.100.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.100.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.100.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.101.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.101.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.101.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.101.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.101.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.101.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.102.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.102.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.102.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.102.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.102.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.102.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.103.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.103.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.103.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.103.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.103.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.103.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.104.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.104.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.104.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.104.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.104.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.104.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.105.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.105.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.105.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.105.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.105.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.105.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.106.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.106.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.106.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.106.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.106.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.106.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.107.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.107.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.107.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.107.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.107.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.107.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.108.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.108.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.108.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.108.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.108.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.108.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.109.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.109.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.109.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.109.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.109.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.109.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.11.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.11.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.11.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.11.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.11.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.11.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.110.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.110.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.110.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.110.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.110.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.110.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.111.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.111.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.111.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.111.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.111.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.111.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.112.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.112.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.112.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.112.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.112.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.112.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.113.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.113.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.113.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.113.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.113.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.113.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.114.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.114.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.114.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.114.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.114.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.114.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.115.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.115.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.115.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.115.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.115.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.115.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.116.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.116.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.116.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.116.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.116.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.116.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.117.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.117.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.117.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.117.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.117.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.117.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.118.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.118.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.118.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.118.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.118.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.118.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.119.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.119.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.119.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.119.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.119.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.119.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.12.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.12.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.12.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.12.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.12.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.12.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.120.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.120.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.120.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.120.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.120.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.120.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.121.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.121.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.121.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.121.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.121.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.121.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.122.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.122.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.122.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.122.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.122.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.122.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.123.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.123.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.123.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.123.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.123.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.123.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.124.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.124.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.124.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.124.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.124.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.124.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.125.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.125.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.125.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.125.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.125.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.125.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.126.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.126.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.126.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.126.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.126.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.126.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.127.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.127.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.127.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.127.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.127.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.127.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.13.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.13.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.13.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.13.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.13.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.13.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.14.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.14.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.14.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.14.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.14.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.14.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.15.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.15.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.15.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.15.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.15.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.15.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.16.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.16.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.16.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.16.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.16.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.16.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.17.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.17.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.17.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.17.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.17.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.17.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.18.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.18.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.18.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.18.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.18.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.18.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.19.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.19.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.19.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.19.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.19.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.19.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.2.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.2.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.2.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.20.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.20.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.20.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.20.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.20.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.20.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.21.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.21.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.21.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.21.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.21.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.21.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.22.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.22.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.22.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.22.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.22.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.22.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.23.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.23.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.23.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.23.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.23.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.23.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.24.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.24.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.24.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.24.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.24.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.24.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.25.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.25.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.25.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.25.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.25.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.25.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.26.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.26.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.26.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.26.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.26.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.26.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.27.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.27.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.27.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.27.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.27.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.27.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.28.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.28.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.28.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.28.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.28.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.28.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.29.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.29.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.29.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.29.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.29.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.29.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.3.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.3.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.3.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.30.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.30.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.30.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.30.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.30.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.30.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.31.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.31.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.31.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.31.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.31.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.31.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.32.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.32.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.32.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.32.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.32.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.32.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.33.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.33.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.33.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.33.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.33.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.33.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.34.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.34.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.34.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.34.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.34.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.34.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.35.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.35.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.35.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.35.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.35.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.35.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.36.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.36.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.36.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.36.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.36.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.36.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.37.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.37.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.37.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.37.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.37.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.37.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.38.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.38.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.38.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.38.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.38.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.38.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.39.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.39.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.39.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.39.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.39.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.39.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.4.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.4.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.4.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.40.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.40.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.40.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.40.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.40.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.40.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.41.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.41.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.41.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.41.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.41.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.41.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.42.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.42.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.42.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.42.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.42.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.42.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.43.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.43.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.43.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.43.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.43.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.43.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.44.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.44.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.44.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.44.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.44.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.44.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.45.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.45.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.45.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.45.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.45.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.45.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.46.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.46.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.46.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.46.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.46.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.46.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.47.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.47.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.47.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.47.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.47.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.47.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.48.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.48.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.48.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.48.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.48.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.48.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.49.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.49.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.49.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.49.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.49.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.49.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.5.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.5.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.5.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.50.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.50.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.50.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.50.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.50.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.50.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.51.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.51.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.51.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.51.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.51.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.51.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.52.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.52.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.52.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.52.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.52.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.52.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.53.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.53.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.53.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.53.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.53.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.53.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.54.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.54.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.54.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.54.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.54.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.54.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.55.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.55.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.55.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.55.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.55.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.55.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.56.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.56.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.56.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.56.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.56.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.56.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.57.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.57.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.57.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.57.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.57.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.57.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.58.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.58.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.58.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.58.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.58.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.58.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.59.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.59.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.59.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.59.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.59.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.59.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.6.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.6.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.6.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.60.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.60.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.60.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.60.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.60.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.60.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.61.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.61.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.61.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.61.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.61.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.61.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.62.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.62.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.62.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.62.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.62.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.62.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.63.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.63.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.63.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.63.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.63.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.63.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.64.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.64.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.64.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.64.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.64.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.64.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.65.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.65.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.65.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.65.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.65.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.65.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.66.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.66.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.66.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.66.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.66.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.66.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.67.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.67.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.67.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.67.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.67.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.67.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.68.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.68.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.68.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.68.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.68.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.68.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.69.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.69.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.69.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.69.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.69.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.69.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.7.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.7.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.7.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.70.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.70.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.70.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.70.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.70.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.70.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.71.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.71.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.71.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.71.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.71.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.71.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.72.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.72.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.72.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.72.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.72.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.72.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.73.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.73.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.73.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.73.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.73.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.73.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.74.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.74.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.74.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.74.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.74.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.74.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.75.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.75.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.75.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.75.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.75.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.75.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.76.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.76.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.76.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.76.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.76.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.76.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.77.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.77.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.77.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.77.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.77.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.77.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.78.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.78.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.78.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.78.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.78.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.78.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.79.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.79.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.79.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.79.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.79.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.79.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.8.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.8.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.8.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.8.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.8.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.8.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.80.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.80.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.80.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.80.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.80.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.80.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.81.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.81.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.81.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.81.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.81.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.81.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.82.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.82.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.82.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.82.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.82.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.82.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.83.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.83.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.83.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.83.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.83.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.83.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.84.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.84.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.84.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.84.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.84.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.84.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.85.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.85.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.85.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.85.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.85.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.85.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.86.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.86.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.86.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.86.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.86.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.86.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.87.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.87.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.87.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.87.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.87.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.87.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.88.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.88.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.88.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.88.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.88.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.88.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.89.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.89.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.89.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.89.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.89.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.89.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.9.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.9.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.9.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.9.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.9.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.9.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.90.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.90.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.90.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.90.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.90.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.90.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.91.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.91.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.91.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.91.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.91.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.91.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.92.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.92.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.92.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.92.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.92.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.92.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.93.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.93.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.93.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.93.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.93.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.93.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.94.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.94.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.94.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.94.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.94.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.94.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.95.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.95.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.95.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.95.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.95.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.95.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.96.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.96.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.96.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.96.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.96.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.96.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.97.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.97.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.97.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.97.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.97.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.97.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.98.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.98.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.98.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.98.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.98.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.98.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.99.w1.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.99.w1.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.99.w2.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.99.w2.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.99.w3.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.experts.99.w3.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.shared_experts.down_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.shared_experts.gate_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.shared_experts.up_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.input_layernorm.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.post_attention_layernorm.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.index_k_norm.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.index_k_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.index_k_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.index_q_norm.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.index_q_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.index_q_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.k_norm.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.k_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.k_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.o_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.o_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.q_norm.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.q_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.q_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.v_proj.weight": "model-00036-of-00059.safetensors", + "language_model.model.layers.36.self_attn.v_proj.weight_scale": "model-00036-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.e_score_correction_bias": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.gate.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.e_score_correction_bias": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.0.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.0.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.0.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.1.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.1.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.1.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.10.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.10.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.10.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.10.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.10.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.10.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.100.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.100.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.100.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.100.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.100.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.100.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.101.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.101.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.101.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.101.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.101.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.101.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.102.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.102.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.102.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.102.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.102.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.102.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.103.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.103.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.103.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.103.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.103.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.103.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.104.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.104.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.104.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.104.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.104.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.104.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.105.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.105.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.105.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.105.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.105.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.105.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.106.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.106.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.106.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.106.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.106.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.106.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.107.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.107.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.107.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.107.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.107.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.107.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.108.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.108.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.108.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.108.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.108.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.108.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.109.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.109.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.109.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.109.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.109.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.109.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.11.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.11.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.11.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.11.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.11.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.11.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.110.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.110.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.110.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.110.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.110.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.110.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.111.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.111.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.111.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.111.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.111.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.111.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.112.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.112.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.112.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.112.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.112.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.112.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.113.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.113.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.113.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.113.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.113.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.113.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.114.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.114.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.114.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.114.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.114.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.114.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.115.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.115.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.115.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.115.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.115.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.115.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.116.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.116.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.116.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.116.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.116.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.116.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.117.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.117.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.117.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.117.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.117.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.117.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.118.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.118.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.118.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.118.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.118.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.118.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.119.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.119.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.119.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.119.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.119.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.119.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.12.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.12.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.12.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.12.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.12.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.12.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.120.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.120.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.120.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.120.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.120.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.120.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.121.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.121.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.121.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.121.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.121.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.121.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.122.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.122.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.122.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.122.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.122.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.122.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.123.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.123.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.123.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.123.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.123.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.123.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.124.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.124.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.124.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.124.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.124.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.124.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.125.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.125.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.125.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.125.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.125.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.125.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.126.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.126.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.126.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.126.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.126.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.126.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.127.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.127.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.127.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.127.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.127.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.127.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.13.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.13.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.13.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.13.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.13.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.13.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.14.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.14.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.14.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.14.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.14.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.14.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.15.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.15.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.15.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.15.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.15.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.15.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.16.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.16.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.16.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.16.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.16.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.16.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.17.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.17.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.17.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.17.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.17.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.17.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.18.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.18.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.18.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.18.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.18.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.18.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.19.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.19.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.19.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.19.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.19.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.19.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.2.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.2.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.2.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.20.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.20.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.20.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.20.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.20.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.20.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.21.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.21.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.21.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.21.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.21.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.21.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.22.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.22.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.22.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.22.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.22.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.22.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.23.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.23.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.23.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.23.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.23.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.23.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.24.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.24.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.24.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.24.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.24.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.24.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.25.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.25.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.25.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.25.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.25.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.25.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.26.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.26.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.26.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.26.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.26.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.26.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.27.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.27.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.27.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.27.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.27.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.27.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.28.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.28.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.28.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.28.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.28.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.28.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.29.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.29.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.29.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.29.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.29.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.29.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.3.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.3.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.3.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.30.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.30.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.30.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.30.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.30.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.30.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.31.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.31.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.31.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.31.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.31.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.31.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.32.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.32.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.32.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.32.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.32.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.32.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.33.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.33.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.33.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.33.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.33.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.33.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.34.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.34.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.34.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.34.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.34.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.34.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.35.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.35.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.35.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.35.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.35.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.35.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.36.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.36.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.36.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.36.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.36.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.36.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.37.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.37.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.37.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.37.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.37.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.37.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.38.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.38.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.38.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.38.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.38.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.38.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.39.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.39.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.39.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.39.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.39.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.39.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.4.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.4.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.4.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.40.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.40.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.40.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.40.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.40.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.40.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.41.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.41.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.41.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.41.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.41.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.41.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.42.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.42.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.42.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.42.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.42.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.42.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.43.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.43.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.43.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.43.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.43.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.43.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.44.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.44.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.44.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.44.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.44.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.44.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.45.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.45.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.45.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.45.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.45.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.45.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.46.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.46.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.46.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.46.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.46.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.46.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.47.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.47.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.47.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.47.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.47.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.47.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.48.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.48.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.48.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.48.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.48.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.48.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.49.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.49.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.49.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.49.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.49.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.49.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.5.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.5.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.5.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.50.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.50.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.50.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.50.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.50.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.50.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.51.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.51.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.51.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.51.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.51.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.51.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.52.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.52.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.52.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.52.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.52.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.52.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.53.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.53.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.53.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.53.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.53.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.53.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.54.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.54.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.54.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.54.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.54.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.54.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.55.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.55.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.55.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.55.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.55.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.55.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.56.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.56.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.56.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.56.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.56.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.56.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.57.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.57.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.57.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.57.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.57.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.57.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.58.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.58.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.58.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.58.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.58.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.58.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.59.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.59.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.59.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.59.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.59.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.59.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.6.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.6.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.6.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.60.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.60.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.60.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.60.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.60.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.60.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.61.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.61.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.61.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.61.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.61.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.61.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.62.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.62.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.62.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.62.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.62.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.62.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.63.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.63.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.63.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.63.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.63.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.63.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.64.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.64.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.64.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.64.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.64.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.64.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.65.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.65.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.65.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.65.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.65.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.65.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.66.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.66.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.66.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.66.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.66.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.66.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.67.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.67.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.67.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.67.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.67.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.67.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.68.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.68.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.68.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.68.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.68.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.68.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.69.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.69.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.69.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.69.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.69.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.69.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.7.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.7.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.7.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.70.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.70.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.70.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.70.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.70.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.70.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.71.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.71.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.71.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.71.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.71.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.71.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.72.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.72.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.72.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.72.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.72.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.72.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.73.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.73.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.73.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.73.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.73.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.73.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.74.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.74.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.74.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.74.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.74.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.74.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.75.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.75.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.75.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.75.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.75.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.75.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.76.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.76.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.76.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.76.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.76.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.76.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.77.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.77.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.77.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.77.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.77.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.77.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.78.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.78.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.78.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.78.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.78.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.78.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.79.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.79.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.79.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.79.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.79.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.79.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.8.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.8.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.8.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.8.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.8.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.8.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.80.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.80.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.80.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.80.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.80.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.80.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.81.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.81.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.81.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.81.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.81.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.81.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.82.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.82.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.82.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.82.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.82.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.82.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.83.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.83.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.83.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.83.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.83.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.83.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.84.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.84.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.84.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.84.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.84.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.84.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.85.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.85.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.85.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.85.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.85.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.85.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.86.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.86.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.86.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.86.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.86.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.86.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.87.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.87.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.87.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.87.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.87.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.87.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.88.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.88.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.88.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.88.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.88.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.88.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.89.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.89.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.89.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.89.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.89.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.89.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.9.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.9.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.9.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.9.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.9.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.9.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.90.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.90.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.90.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.90.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.90.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.90.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.91.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.91.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.91.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.91.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.91.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.91.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.92.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.92.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.92.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.92.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.92.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.92.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.93.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.93.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.93.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.93.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.93.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.93.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.94.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.94.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.94.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.94.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.94.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.94.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.95.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.95.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.95.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.95.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.95.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.95.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.96.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.96.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.96.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.96.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.96.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.96.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.97.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.97.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.97.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.97.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.97.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.97.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.98.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.98.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.98.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.98.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.98.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.98.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.99.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.99.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.99.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.99.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.99.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.experts.99.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.shared_experts.down_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.shared_experts.gate_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.shared_experts.up_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.index_k_norm.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.index_k_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.index_k_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.index_q_norm.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.index_q_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.index_q_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.k_norm.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.q_norm.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.0.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.0.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.0.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.1.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.1.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.1.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.10.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.10.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.10.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.10.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.10.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.10.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.100.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.100.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.100.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.100.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.100.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.100.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.101.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.101.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.101.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.101.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.101.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.101.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.102.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.102.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.102.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.102.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.102.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.102.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.103.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.103.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.103.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.103.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.103.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.103.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.104.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.104.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.104.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.104.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.104.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.104.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.105.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.105.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.105.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.105.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.105.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.105.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.106.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.106.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.106.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.106.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.106.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.106.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.107.w1.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.107.w1.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.107.w2.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.107.w2.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.107.w3.weight": "model-00021-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.107.w3.weight_scale": "model-00021-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.e_score_correction_bias": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.gate.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.e_score_correction_bias": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.0.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.0.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.0.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.1.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.1.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.1.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.10.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.10.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.10.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.100.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.100.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.100.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.101.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.101.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.101.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.102.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.102.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.102.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.103.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.103.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.103.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.104.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.104.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.104.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.105.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.105.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.105.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.106.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.106.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.106.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.107.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.107.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.107.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.108.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.108.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.108.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.109.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.109.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.109.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.11.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.11.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.11.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.110.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.110.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.110.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.111.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.111.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.111.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.112.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.112.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.112.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.112.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.112.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.112.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.113.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.113.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.113.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.113.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.113.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.113.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.114.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.114.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.114.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.114.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.114.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.114.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.115.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.115.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.115.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.115.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.115.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.115.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.116.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.116.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.116.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.116.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.116.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.116.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.117.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.117.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.117.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.117.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.117.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.117.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.118.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.118.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.118.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.118.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.118.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.118.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.119.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.119.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.119.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.119.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.119.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.119.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.12.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.12.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.12.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.120.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.120.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.120.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.120.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.120.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.120.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.121.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.121.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.121.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.121.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.121.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.121.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.122.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.122.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.122.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.122.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.122.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.122.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.123.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.123.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.123.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.123.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.123.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.123.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.124.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.124.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.124.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.124.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.124.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.124.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.125.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.125.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.125.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.125.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.125.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.125.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.126.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.126.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.126.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.126.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.126.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.126.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.127.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.127.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.127.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.127.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.127.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.127.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.13.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.13.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.13.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.14.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.14.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.14.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.15.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.15.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.15.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.16.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.16.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.16.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.16.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.16.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.16.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.17.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.17.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.17.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.17.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.17.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.17.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.18.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.18.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.18.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.18.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.18.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.18.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.19.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.19.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.19.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.19.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.19.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.19.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.2.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.2.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.2.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.20.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.20.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.20.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.20.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.20.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.20.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.21.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.21.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.21.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.21.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.21.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.21.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.22.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.22.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.22.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.22.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.22.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.22.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.23.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.23.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.23.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.23.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.23.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.23.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.24.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.24.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.24.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.24.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.24.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.24.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.25.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.25.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.25.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.25.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.25.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.25.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.26.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.26.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.26.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.26.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.26.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.26.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.27.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.27.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.27.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.27.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.27.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.27.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.28.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.28.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.28.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.28.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.28.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.28.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.29.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.29.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.29.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.29.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.29.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.29.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.3.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.3.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.3.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.30.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.30.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.30.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.30.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.30.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.30.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.31.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.31.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.31.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.31.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.31.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.31.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.32.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.32.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.32.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.32.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.32.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.32.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.33.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.33.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.33.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.33.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.33.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.33.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.34.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.34.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.34.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.34.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.34.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.34.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.35.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.35.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.35.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.35.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.35.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.35.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.36.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.36.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.36.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.36.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.36.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.36.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.37.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.37.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.37.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.37.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.37.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.37.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.38.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.38.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.38.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.38.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.38.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.38.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.39.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.39.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.39.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.39.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.39.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.39.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.4.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.4.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.4.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.40.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.40.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.40.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.40.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.40.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.40.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.41.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.41.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.41.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.41.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.41.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.41.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.42.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.42.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.42.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.42.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.42.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.42.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.43.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.43.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.43.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.43.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.43.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.43.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.44.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.44.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.44.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.44.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.44.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.44.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.45.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.45.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.45.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.45.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.45.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.45.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.46.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.46.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.46.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.46.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.46.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.46.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.47.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.47.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.47.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.47.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.47.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.47.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.48.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.48.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.48.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.48.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.48.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.48.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.49.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.49.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.49.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.49.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.49.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.49.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.5.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.5.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.5.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.50.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.50.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.50.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.50.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.50.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.50.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.51.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.51.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.51.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.51.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.51.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.51.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.52.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.52.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.52.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.52.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.52.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.52.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.53.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.53.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.53.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.53.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.53.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.53.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.54.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.54.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.54.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.54.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.54.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.54.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.55.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.55.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.55.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.55.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.55.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.55.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.56.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.56.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.56.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.56.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.56.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.56.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.57.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.57.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.57.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.57.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.57.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.57.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.58.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.58.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.58.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.58.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.58.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.58.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.59.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.59.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.59.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.59.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.59.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.59.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.6.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.6.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.6.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.60.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.60.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.60.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.60.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.60.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.60.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.61.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.61.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.61.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.61.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.61.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.61.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.62.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.62.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.62.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.62.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.62.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.62.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.63.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.63.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.63.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.63.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.63.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.63.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.64.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.64.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.64.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.64.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.64.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.64.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.65.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.65.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.65.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.65.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.65.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.65.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.66.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.66.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.66.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.66.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.66.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.66.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.67.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.67.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.67.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.67.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.67.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.67.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.68.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.68.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.68.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.68.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.68.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.68.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.69.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.69.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.69.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.69.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.69.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.69.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.7.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.7.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.7.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.70.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.70.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.70.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.70.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.70.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.70.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.71.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.71.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.71.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.71.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.71.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.71.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.72.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.72.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.72.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.72.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.72.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.72.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.73.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.73.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.73.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.73.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.73.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.73.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.74.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.74.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.74.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.74.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.74.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.74.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.75.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.75.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.75.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.75.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.75.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.75.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.76.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.76.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.76.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.76.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.76.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.76.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.77.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.77.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.77.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.77.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.77.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.77.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.78.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.78.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.78.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.78.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.78.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.78.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.79.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.79.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.79.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.79.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.79.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.79.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.8.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.8.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.8.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.80.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.80.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.80.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.80.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.80.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.80.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.81.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.81.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.81.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.81.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.81.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.81.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.82.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.82.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.82.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.82.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.82.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.82.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.83.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.83.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.83.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.83.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.83.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.83.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.84.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.84.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.84.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.84.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.84.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.84.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.85.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.85.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.85.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.85.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.85.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.85.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.86.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.86.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.86.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.86.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.86.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.86.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.87.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.87.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.87.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.87.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.87.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.87.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.88.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.88.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.88.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.88.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.88.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.88.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.89.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.89.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.89.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.89.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.89.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.89.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.9.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.9.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.9.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.90.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.90.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.90.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.90.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.90.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.90.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.91.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.91.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.91.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.91.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.91.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.91.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.92.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.92.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.92.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.92.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.92.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.92.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.93.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.93.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.93.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.93.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.93.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.93.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.94.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.94.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.94.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.94.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.94.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.94.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.95.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.95.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.95.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.95.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.95.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.95.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.96.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.96.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.96.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.96.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.96.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.96.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.97.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.97.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.97.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.97.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.97.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.97.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.98.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.98.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.98.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.98.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.98.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.98.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.99.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.99.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.99.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.99.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.99.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.experts.99.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.shared_experts.down_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.shared_experts.gate_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.shared_experts.up_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.index_k_norm.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.index_k_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.index_k_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.index_q_norm.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.index_q_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.index_q_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.k_norm.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.q_norm.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.0.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.0.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.0.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.1.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.1.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.1.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.10.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.10.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.10.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.100.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.100.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.100.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.101.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.101.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.101.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.102.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.102.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.102.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.103.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.103.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.103.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.104.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.104.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.104.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.105.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.105.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.105.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.106.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.106.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.106.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.107.w1.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.107.w2.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00059.safetensors", + "language_model.model.layers.50.block_sparse_moe.experts.107.w3.weight_scale": "model-00016-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.gate.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.108.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.108.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.108.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.108.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.108.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.108.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.109.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.109.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.109.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.109.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.109.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.109.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.11.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.11.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.11.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.11.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.11.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.11.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.110.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.110.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.110.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.110.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.110.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.110.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.111.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.111.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.111.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.111.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.111.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.111.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.112.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.112.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.112.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.112.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.112.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.112.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.113.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.113.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.113.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.113.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.113.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.113.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.114.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.114.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.114.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.114.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.114.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.114.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.115.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.115.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.115.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.115.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.115.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.115.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.116.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.116.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.116.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.116.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.116.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.116.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.117.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.117.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.117.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.117.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.117.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.117.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.118.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.118.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.118.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.118.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.118.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.118.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.119.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.119.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.119.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.119.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.119.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.119.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.12.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.12.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.12.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.12.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.12.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.12.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.120.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.120.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.120.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.120.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.120.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.120.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.121.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.121.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.121.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.121.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.121.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.121.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.122.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.122.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.122.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.122.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.122.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.122.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.123.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.123.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.123.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.123.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.123.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.123.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.124.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.124.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.124.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.124.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.124.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.124.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.125.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.125.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.125.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.125.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.125.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.125.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.126.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.126.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.126.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.126.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.126.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.126.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.127.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.127.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.127.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.127.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.127.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.127.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.13.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.13.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.13.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.13.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.13.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.13.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.14.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.14.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.14.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.14.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.14.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.14.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.15.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.15.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.15.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.15.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.15.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.15.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.16.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.16.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.16.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.16.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.16.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.16.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.17.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.17.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.17.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.17.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.17.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.17.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.18.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.18.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.18.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.18.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.18.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.18.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.19.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.19.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.19.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.19.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.19.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.19.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.2.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.2.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.2.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.20.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.20.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.20.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.20.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.20.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.20.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.21.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.21.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.21.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.21.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.21.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.21.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.22.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.22.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.22.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.22.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.22.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.22.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.23.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.23.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.23.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.23.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.23.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.23.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.24.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.24.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.24.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.24.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.24.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.24.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.25.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.25.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.25.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.25.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.25.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.25.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.26.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.26.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.26.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.26.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.26.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.26.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.27.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.27.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.27.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.27.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.27.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.27.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.28.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.28.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.28.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.28.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.28.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.28.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.29.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.29.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.29.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.29.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.29.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.29.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.3.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.3.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.3.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.3.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.3.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.3.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.30.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.30.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.30.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.30.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.30.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.30.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.31.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.31.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.31.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.31.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.31.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.31.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.32.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.32.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.32.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.32.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.32.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.32.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.33.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.33.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.33.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.33.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.33.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.33.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.34.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.34.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.34.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.34.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.34.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.34.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.35.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.35.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.35.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.35.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.35.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.35.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.36.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.36.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.36.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.36.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.36.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.36.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.37.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.37.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.37.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.37.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.37.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.37.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.38.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.38.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.38.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.38.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.38.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.38.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.39.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.39.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.39.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.39.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.39.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.39.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.4.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.4.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.4.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.4.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.4.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.4.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.40.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.40.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.40.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.40.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.40.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.40.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.41.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.41.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.41.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.41.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.41.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.41.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.42.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.42.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.42.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.42.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.42.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.42.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.43.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.43.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.43.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.43.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.43.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.43.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.44.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.44.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.44.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.44.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.44.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.44.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.45.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.45.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.45.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.45.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.45.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.45.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.46.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.46.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.46.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.46.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.46.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.46.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.47.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.47.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.47.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.47.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.47.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.47.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.48.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.48.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.48.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.48.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.48.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.48.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.49.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.49.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.49.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.49.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.49.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.49.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.5.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.5.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.5.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.5.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.5.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.5.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.50.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.50.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.50.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.50.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.50.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.50.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.51.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.51.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.51.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.51.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.51.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.51.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.52.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.52.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.52.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.52.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.52.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.52.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.53.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.53.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.53.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.53.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.53.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.53.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.54.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.54.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.54.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.54.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.54.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.54.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.55.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.55.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.55.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.55.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.55.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.55.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.56.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.56.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.56.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.56.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.56.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.56.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.57.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.57.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.57.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.57.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.57.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.57.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.58.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.58.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.58.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.58.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.58.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.58.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.59.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.59.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.59.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.59.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.59.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.59.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.6.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.6.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.6.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.6.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.6.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.6.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.60.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.60.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.60.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.60.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.60.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.60.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.61.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.61.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.61.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.61.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.61.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.61.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.62.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.62.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.62.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.62.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.62.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.62.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.63.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.63.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.63.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.63.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.63.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.63.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.64.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.64.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.64.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.64.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.64.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.64.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.65.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.65.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.65.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.65.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.65.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.65.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.66.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.66.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.66.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.66.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.66.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.66.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.67.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.67.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.67.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.67.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.67.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.67.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.68.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.68.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.68.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.68.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.68.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.68.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.69.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.69.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.69.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.69.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.69.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.69.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.7.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.7.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.7.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.7.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.7.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.7.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.70.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.70.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.70.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.70.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.70.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.70.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.71.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.71.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.71.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.71.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.71.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.71.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.72.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.72.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.72.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.72.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.72.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.72.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.73.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.73.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.73.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.73.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.73.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.73.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.74.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.74.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.74.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.74.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.74.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.74.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.75.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.75.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.75.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.75.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.75.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.75.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.76.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.76.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.76.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.76.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.76.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.76.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.77.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.77.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.77.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.77.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.77.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.77.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.78.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.78.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.78.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.78.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.78.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.78.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.79.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.79.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.79.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.79.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.79.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.79.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.8.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.8.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.8.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.8.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.8.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.8.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.80.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.80.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.80.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.80.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.80.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.80.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.81.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.81.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.81.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.81.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.81.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.81.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.82.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.82.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.82.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.82.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.82.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.82.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.83.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.83.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.83.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.83.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.83.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.83.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.84.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.84.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.84.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.84.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.84.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.84.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.85.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.85.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.85.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.85.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.85.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.85.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.86.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.86.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.86.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.86.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.86.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.86.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.87.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.87.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.87.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.87.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.87.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.87.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.88.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.88.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.88.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.88.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.88.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.88.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.89.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.89.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.89.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.89.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.89.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.89.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.9.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.9.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.9.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.9.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.9.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.9.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.90.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.90.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.90.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.90.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.90.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.90.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.91.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.91.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.91.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.91.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.91.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.91.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.92.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.92.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.92.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.92.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.92.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.92.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.93.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.93.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.93.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.93.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.93.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.93.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.94.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.94.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.94.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.94.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.94.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.94.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.95.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.95.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.95.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.95.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.95.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.95.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.96.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.96.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.96.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.96.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.96.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.96.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.97.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.97.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.97.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.97.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.97.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.97.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.98.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.98.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.98.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.98.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.98.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.98.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.99.w1.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.99.w1.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.99.w2.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.99.w2.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.99.w3.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.experts.99.w3.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.shared_experts.down_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.shared_experts.gate_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.shared_experts.up_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.input_layernorm.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.post_attention_layernorm.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.index_k_norm.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.index_k_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.index_k_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.index_q_norm.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.index_q_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.index_q_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.k_norm.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.k_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.k_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.o_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.o_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.q_norm.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.q_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.q_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.v_proj.weight": "model-00049-of-00059.safetensors", + "language_model.model.layers.49.self_attn.v_proj.weight_scale": "model-00049-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.e_score_correction_bias": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.gate.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.e_score_correction_bias": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.0.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.0.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.0.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.1.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.1.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.1.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.10.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.10.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.10.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.100.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.100.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.100.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.101.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.101.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.101.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.102.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.102.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.102.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.103.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.103.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.103.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.104.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.104.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.104.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.105.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.105.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.105.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.106.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.106.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.106.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.107.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.107.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.107.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.108.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.108.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.108.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.109.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.109.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.109.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.11.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.11.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.11.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.110.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.110.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.110.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.111.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.111.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.111.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.112.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.112.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.112.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.113.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.113.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.113.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.114.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.114.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.114.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.115.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.115.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.115.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.116.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.116.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.116.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.116.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.116.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.116.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.117.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.117.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.117.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.117.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.117.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.117.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.118.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.118.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.118.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.118.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.118.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.118.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.119.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.119.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.119.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.119.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.119.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.119.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.12.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.12.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.12.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.120.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.120.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.120.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.120.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.120.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.120.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.121.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.121.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.121.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.121.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.121.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.121.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.122.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.122.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.122.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.122.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.122.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.122.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.123.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.123.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.123.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.123.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.123.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.123.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.124.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.124.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.124.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.124.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.124.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.124.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.125.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.125.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.125.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.125.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.125.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.125.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.126.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.126.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.126.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.126.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.126.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.126.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.127.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.127.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.127.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.127.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.127.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.127.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.13.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.13.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.13.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.14.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.14.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.14.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.15.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.15.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.15.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.16.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.16.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.16.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.17.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.17.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.17.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.18.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.18.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.18.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.19.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.19.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.19.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.2.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.2.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.2.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.20.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.20.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.20.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.21.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.21.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.21.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.22.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.22.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.22.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.23.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.23.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.23.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.24.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.24.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.24.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.25.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.25.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.25.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.26.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.26.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.26.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.27.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.27.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.27.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.28.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.28.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.28.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.29.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.29.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.29.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.3.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.3.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.3.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.30.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.30.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.30.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.31.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.31.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.31.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.32.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.32.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.32.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.32.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.32.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.32.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.33.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.33.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.33.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.33.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.33.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.33.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.34.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.34.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.34.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.34.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.34.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.34.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.35.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.35.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.35.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.35.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.35.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.35.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.36.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.36.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.36.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.36.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.36.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.36.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.37.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.37.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.37.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.37.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.37.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.37.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.38.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.38.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.38.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.38.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.38.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.38.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.39.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.39.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.39.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.39.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.39.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.39.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.4.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.4.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.4.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.40.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.40.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.40.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.40.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.40.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.40.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.41.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.41.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.41.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.41.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.41.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.41.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.42.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.42.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.42.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.42.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.42.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.42.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.43.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.43.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.43.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.43.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.43.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.43.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.44.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.44.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.44.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.44.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.44.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.44.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.45.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.45.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.45.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.45.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.45.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.45.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.46.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.46.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.46.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.46.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.46.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.46.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.47.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.47.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.47.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.47.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.47.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.47.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.48.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.48.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.48.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.48.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.48.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.48.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.49.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.49.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.49.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.49.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.49.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.49.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.5.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.5.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.5.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.50.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.50.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.50.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.50.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.50.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.50.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.51.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.51.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.51.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.51.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.51.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.51.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.52.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.52.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.52.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.52.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.52.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.52.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.53.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.53.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.53.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.53.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.53.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.53.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.54.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.54.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.54.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.54.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.54.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.54.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.55.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.55.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.55.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.55.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.55.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.55.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.56.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.56.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.56.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.56.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.56.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.56.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.57.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.57.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.57.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.57.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.57.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.57.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.58.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.58.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.58.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.58.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.58.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.58.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.59.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.59.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.59.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.59.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.59.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.59.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.6.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.6.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.6.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.60.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.60.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.60.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.60.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.60.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.60.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.61.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.61.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.61.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.61.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.61.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.61.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.62.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.62.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.62.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.62.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.62.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.62.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.63.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.63.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.63.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.63.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.63.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.63.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.64.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.64.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.64.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.64.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.64.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.64.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.65.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.65.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.65.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.65.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.65.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.65.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.66.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.66.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.66.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.66.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.66.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.66.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.67.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.67.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.67.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.67.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.67.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.67.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.68.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.68.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.68.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.68.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.68.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.68.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.69.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.69.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.69.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.69.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.69.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.69.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.7.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.7.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.7.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.70.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.70.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.70.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.70.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.70.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.70.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.71.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.71.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.71.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.71.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.71.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.71.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.72.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.72.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.72.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.72.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.72.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.72.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.73.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.73.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.73.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.73.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.73.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.73.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.74.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.74.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.74.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.74.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.74.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.74.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.75.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.75.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.75.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.75.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.75.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.75.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.76.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.76.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.76.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.76.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.76.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.76.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.77.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.77.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.77.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.77.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.77.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.77.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.78.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.78.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.78.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.78.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.78.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.78.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.79.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.79.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.79.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.79.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.79.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.79.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.8.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.8.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.8.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.80.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.80.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.80.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.80.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.80.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.80.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.81.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.81.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.81.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.81.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.81.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.81.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.82.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.82.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.82.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.82.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.82.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.82.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.83.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.83.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.83.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.83.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.83.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.83.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.84.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.84.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.84.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.84.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.84.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.84.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.85.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.85.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.85.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.85.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.85.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.85.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.86.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.86.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.86.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.86.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.86.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.86.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.87.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.87.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.87.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.87.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.87.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.87.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.88.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.88.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.88.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.88.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.88.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.88.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.89.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.89.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.89.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.89.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.89.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.89.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.9.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.9.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.9.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.90.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.90.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.90.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.90.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.90.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.90.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.91.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.91.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.91.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.91.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.91.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.91.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.92.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.92.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.92.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.92.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.92.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.92.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.93.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.93.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.93.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.93.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.93.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.93.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.94.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.94.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.94.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.94.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.94.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.94.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.95.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.95.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.95.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.95.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.95.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.95.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.96.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.96.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.96.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.96.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.96.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.96.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.97.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.97.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.97.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.97.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.97.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.97.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.98.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.98.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.98.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.98.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.98.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.98.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.99.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.99.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.99.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.99.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.99.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.experts.99.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.shared_experts.down_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.shared_experts.gate_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.shared_experts.up_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.index_k_norm.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.index_k_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.index_k_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.index_q_norm.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.index_q_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.index_q_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.k_norm.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.q_norm.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.0.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.0.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.0.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.1.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.1.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.1.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.10.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.10.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.10.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.100.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.100.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.100.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.101.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.101.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.101.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.102.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.102.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.102.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.103.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.103.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.103.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.104.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.104.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.104.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.105.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.105.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.105.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.106.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.106.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.106.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.107.w1.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.107.w2.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.107.w3.weight_scale": "model-00011-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.gate.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.108.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.108.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.108.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.108.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.108.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.108.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.109.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.109.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.109.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.109.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.109.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.109.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.11.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.11.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.11.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.11.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.11.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.11.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.110.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.110.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.110.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.110.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.110.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.110.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.111.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.111.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.111.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.111.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.111.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.111.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.112.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.112.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.112.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.112.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.112.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.112.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.113.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.113.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.113.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.113.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.113.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.113.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.114.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.114.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.114.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.114.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.114.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.114.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.115.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.115.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.115.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.115.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.115.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.115.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.116.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.116.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.116.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.116.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.116.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.116.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.117.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.117.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.117.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.117.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.117.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.117.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.118.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.118.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.118.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.118.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.118.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.118.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.119.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.119.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.119.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.119.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.119.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.119.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.12.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.12.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.12.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.12.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.12.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.12.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.120.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.120.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.120.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.120.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.120.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.120.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.121.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.121.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.121.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.121.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.121.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.121.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.122.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.122.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.122.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.122.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.122.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.122.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.123.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.123.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.123.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.123.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.123.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.123.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.124.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.124.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.124.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.124.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.124.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.124.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.125.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.125.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.125.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.125.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.125.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.125.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.126.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.126.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.126.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.126.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.126.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.126.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.127.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.127.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.127.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.127.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.127.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.127.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.13.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.13.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.13.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.13.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.13.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.13.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.14.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.14.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.14.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.14.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.14.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.14.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.15.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.15.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.15.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.15.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.15.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.15.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.16.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.16.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.16.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.16.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.16.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.16.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.17.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.17.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.17.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.17.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.17.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.17.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.18.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.18.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.18.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.18.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.18.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.18.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.19.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.19.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.19.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.19.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.19.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.19.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.2.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.2.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.2.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.20.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.20.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.20.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.20.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.20.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.20.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.21.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.21.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.21.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.21.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.21.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.21.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.22.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.22.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.22.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.22.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.22.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.22.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.23.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.23.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.23.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.23.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.23.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.23.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.24.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.24.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.24.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.24.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.24.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.24.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.25.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.25.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.25.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.25.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.25.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.25.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.26.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.26.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.26.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.26.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.26.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.26.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.27.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.27.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.27.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.27.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.27.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.27.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.28.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.28.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.28.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.28.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.28.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.28.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.29.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.29.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.29.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.29.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.29.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.29.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.3.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.3.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.3.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.3.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.3.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.3.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.30.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.30.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.30.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.30.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.30.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.30.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.31.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.31.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.31.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.31.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.31.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.31.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.32.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.32.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.32.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.32.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.32.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.32.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.33.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.33.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.33.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.33.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.33.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.33.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.34.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.34.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.34.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.34.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.34.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.34.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.35.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.35.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.35.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.35.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.35.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.35.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.36.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.36.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.36.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.36.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.36.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.36.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.37.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.37.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.37.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.37.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.37.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.37.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.38.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.38.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.38.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.38.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.38.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.38.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.39.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.39.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.39.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.39.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.39.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.39.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.4.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.4.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.4.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.4.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.4.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.4.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.40.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.40.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.40.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.40.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.40.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.40.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.41.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.41.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.41.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.41.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.41.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.41.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.42.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.42.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.42.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.42.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.42.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.42.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.43.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.43.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.43.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.43.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.43.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.43.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.44.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.44.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.44.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.44.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.44.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.44.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.45.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.45.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.45.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.45.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.45.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.45.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.46.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.46.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.46.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.46.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.46.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.46.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.47.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.47.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.47.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.47.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.47.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.47.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.48.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.48.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.48.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.48.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.48.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.48.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.49.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.49.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.49.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.49.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.49.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.49.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.5.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.5.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.5.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.5.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.5.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.5.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.50.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.50.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.50.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.50.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.50.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.50.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.51.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.51.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.51.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.51.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.51.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.51.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.52.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.52.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.52.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.52.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.52.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.52.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.53.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.53.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.53.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.53.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.53.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.53.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.54.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.54.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.54.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.54.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.54.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.54.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.55.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.55.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.55.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.55.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.55.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.55.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.56.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.56.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.56.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.56.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.56.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.56.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.57.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.57.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.57.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.57.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.57.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.57.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.58.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.58.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.58.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.58.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.58.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.58.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.59.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.59.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.59.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.59.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.59.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.59.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.6.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.6.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.6.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.6.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.6.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.6.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.60.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.60.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.60.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.60.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.60.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.60.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.61.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.61.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.61.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.61.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.61.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.61.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.62.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.62.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.62.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.62.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.62.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.62.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.63.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.63.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.63.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.63.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.63.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.63.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.64.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.64.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.64.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.64.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.64.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.64.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.65.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.65.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.65.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.65.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.65.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.65.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.66.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.66.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.66.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.66.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.66.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.66.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.67.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.67.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.67.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.67.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.67.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.67.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.68.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.68.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.68.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.68.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.68.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.68.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.69.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.69.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.69.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.69.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.69.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.69.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.7.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.7.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.7.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.7.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.7.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.7.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.70.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.70.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.70.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.70.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.70.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.70.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.71.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.71.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.71.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.71.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.71.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.71.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.72.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.72.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.72.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.72.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.72.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.72.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.73.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.73.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.73.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.73.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.73.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.73.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.74.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.74.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.74.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.74.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.74.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.74.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.75.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.75.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.75.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.75.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.75.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.75.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.76.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.76.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.76.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.76.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.76.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.76.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.77.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.77.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.77.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.77.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.77.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.77.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.78.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.78.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.78.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.78.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.78.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.78.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.79.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.79.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.79.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.79.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.79.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.79.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.8.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.8.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.8.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.8.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.8.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.8.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.80.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.80.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.80.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.80.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.80.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.80.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.81.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.81.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.81.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.81.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.81.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.81.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.82.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.82.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.82.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.82.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.82.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.82.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.83.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.83.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.83.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.83.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.83.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.83.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.84.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.84.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.84.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.84.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.84.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.84.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.85.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.85.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.85.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.85.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.85.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.85.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.86.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.86.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.86.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.86.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.86.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.86.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.87.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.87.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.87.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.87.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.87.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.87.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.88.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.88.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.88.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.88.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.88.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.88.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.89.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.89.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.89.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.89.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.89.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.89.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.9.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.9.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.9.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.9.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.9.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.9.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.90.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.90.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.90.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.90.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.90.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.90.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.91.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.91.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.91.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.91.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.91.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.91.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.92.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.92.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.92.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.92.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.92.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.92.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.93.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.93.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.93.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.93.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.93.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.93.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.94.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.94.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.94.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.94.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.94.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.94.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.95.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.95.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.95.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.95.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.95.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.95.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.96.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.96.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.96.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.96.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.96.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.96.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.97.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.97.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.97.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.97.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.97.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.97.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.98.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.98.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.98.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.98.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.98.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.98.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.99.w1.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.99.w1.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.99.w2.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.99.w2.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.99.w3.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.experts.99.w3.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.shared_experts.down_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.shared_experts.gate_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.shared_experts.up_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.input_layernorm.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.post_attention_layernorm.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.index_k_norm.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.index_k_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.index_k_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.index_q_norm.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.index_q_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.index_q_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.k_norm.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.k_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.k_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.o_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.o_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.q_norm.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.q_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.q_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.v_proj.weight": "model-00055-of-00059.safetensors", + "language_model.model.layers.55.self_attn.v_proj.weight_scale": "model-00055-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.e_score_correction_bias": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.gate.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.e_score_correction_bias": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.0.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.0.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.0.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.1.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.1.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.1.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.10.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.10.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.10.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.100.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.100.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.100.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.101.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.101.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.101.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.102.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.102.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.102.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.103.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.103.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.103.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.104.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.104.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.104.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.105.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.105.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.105.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.106.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.106.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.106.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.107.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.107.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.107.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.108.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.108.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.108.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.108.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.108.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.108.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.109.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.109.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.109.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.109.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.109.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.109.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.11.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.11.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.11.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.11.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.11.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.11.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.110.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.110.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.110.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.110.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.110.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.110.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.111.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.111.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.111.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.111.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.111.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.111.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.112.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.112.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.112.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.112.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.112.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.112.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.113.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.113.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.113.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.113.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.113.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.113.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.114.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.114.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.114.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.114.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.114.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.114.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.115.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.115.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.115.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.115.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.115.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.115.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.116.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.116.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.116.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.116.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.116.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.116.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.117.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.117.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.117.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.117.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.117.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.117.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.118.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.118.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.118.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.118.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.118.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.118.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.119.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.119.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.119.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.119.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.119.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.119.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.12.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.12.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.12.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.12.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.12.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.12.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.120.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.120.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.120.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.120.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.120.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.120.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.121.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.121.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.121.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.121.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.121.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.121.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.122.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.122.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.122.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.122.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.122.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.122.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.123.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.123.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.123.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.123.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.123.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.123.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.124.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.124.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.124.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.124.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.124.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.124.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.125.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.125.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.125.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.125.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.125.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.125.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.126.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.126.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.126.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.126.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.126.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.126.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.127.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.127.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.127.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.127.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.127.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.127.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.13.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.13.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.13.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.13.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.13.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.13.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.14.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.14.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.14.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.14.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.14.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.14.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.15.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.15.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.15.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.15.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.15.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.15.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.16.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.16.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.16.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.16.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.16.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.16.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.17.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.17.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.17.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.17.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.17.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.17.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.18.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.18.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.18.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.18.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.18.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.18.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.19.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.19.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.19.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.19.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.19.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.19.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.2.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.2.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.2.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.20.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.20.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.20.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.20.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.20.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.20.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.21.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.21.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.21.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.21.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.21.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.21.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.22.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.22.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.22.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.22.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.22.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.22.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.23.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.23.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.23.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.23.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.23.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.23.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.24.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.24.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.24.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.24.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.24.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.24.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.25.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.25.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.25.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.25.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.25.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.25.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.26.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.26.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.26.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.26.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.26.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.26.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.27.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.27.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.27.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.27.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.27.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.27.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.28.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.28.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.28.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.28.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.28.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.28.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.29.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.29.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.29.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.29.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.29.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.29.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.3.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.3.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.3.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.30.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.30.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.30.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.30.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.30.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.30.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.31.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.31.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.31.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.31.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.31.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.31.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.32.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.32.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.32.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.32.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.32.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.32.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.33.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.33.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.33.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.33.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.33.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.33.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.34.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.34.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.34.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.34.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.34.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.34.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.35.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.35.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.35.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.35.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.35.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.35.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.36.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.36.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.36.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.36.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.36.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.36.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.37.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.37.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.37.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.37.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.37.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.37.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.38.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.38.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.38.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.38.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.38.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.38.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.39.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.39.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.39.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.39.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.39.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.39.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.4.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.4.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.4.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.40.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.40.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.40.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.40.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.40.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.40.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.41.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.41.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.41.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.41.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.41.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.41.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.42.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.42.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.42.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.42.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.42.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.42.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.43.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.43.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.43.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.43.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.43.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.43.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.44.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.44.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.44.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.44.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.44.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.44.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.45.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.45.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.45.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.45.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.45.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.45.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.46.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.46.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.46.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.46.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.46.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.46.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.47.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.47.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.47.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.47.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.47.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.47.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.48.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.48.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.48.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.48.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.48.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.48.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.49.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.49.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.49.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.49.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.49.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.49.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.5.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.5.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.5.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.50.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.50.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.50.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.50.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.50.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.50.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.51.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.51.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.51.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.51.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.51.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.51.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.52.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.52.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.52.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.52.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.52.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.52.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.53.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.53.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.53.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.53.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.53.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.53.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.54.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.54.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.54.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.54.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.54.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.54.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.55.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.55.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.55.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.55.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.55.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.55.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.56.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.56.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.56.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.56.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.56.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.56.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.57.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.57.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.57.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.57.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.57.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.57.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.58.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.58.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.58.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.58.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.58.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.58.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.59.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.59.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.59.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.59.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.59.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.59.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.6.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.6.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.6.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.60.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.60.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.60.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.60.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.60.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.60.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.61.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.61.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.61.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.61.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.61.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.61.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.62.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.62.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.62.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.62.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.62.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.62.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.63.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.63.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.63.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.63.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.63.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.63.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.64.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.64.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.64.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.64.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.64.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.64.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.65.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.65.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.65.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.65.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.65.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.65.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.66.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.66.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.66.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.66.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.66.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.66.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.67.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.67.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.67.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.67.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.67.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.67.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.68.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.68.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.68.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.68.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.68.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.68.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.69.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.69.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.69.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.69.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.69.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.69.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.7.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.7.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.7.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.70.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.70.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.70.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.70.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.70.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.70.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.71.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.71.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.71.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.71.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.71.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.71.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.72.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.72.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.72.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.72.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.72.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.72.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.73.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.73.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.73.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.73.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.73.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.73.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.74.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.74.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.74.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.74.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.74.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.74.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.75.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.75.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.75.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.75.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.75.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.75.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.76.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.76.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.76.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.76.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.76.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.76.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.77.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.77.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.77.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.77.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.77.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.77.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.78.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.78.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.78.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.78.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.78.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.78.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.79.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.79.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.79.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.79.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.79.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.79.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.8.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.8.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.8.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.8.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.8.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.8.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.80.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.80.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.80.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.80.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.80.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.80.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.81.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.81.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.81.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.81.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.81.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.81.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.82.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.82.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.82.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.82.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.82.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.82.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.83.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.83.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.83.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.83.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.83.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.83.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.84.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.84.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.84.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.84.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.84.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.84.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.85.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.85.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.85.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.85.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.85.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.85.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.86.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.86.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.86.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.86.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.86.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.86.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.87.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.87.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.87.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.87.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.87.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.87.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.88.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.88.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.88.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.88.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.88.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.88.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.89.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.89.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.89.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.89.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.89.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.89.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.9.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.9.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.9.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.9.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.9.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.9.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.90.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.90.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.90.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.90.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.90.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.90.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.91.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.91.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.91.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.91.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.91.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.91.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.92.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.92.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.92.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.92.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.92.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.92.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.93.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.93.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.93.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.93.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.93.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.93.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.94.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.94.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.94.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.94.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.94.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.94.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.95.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.95.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.95.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.95.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.95.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.95.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.96.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.96.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.96.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.96.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.96.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.96.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.97.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.97.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.97.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.97.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.97.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.97.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.98.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.98.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.98.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.98.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.98.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.98.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.99.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.99.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.99.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.99.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.99.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.experts.99.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.shared_experts.down_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.shared_experts.gate_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.shared_experts.up_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.index_k_norm.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.index_k_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.index_k_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.index_q_norm.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.index_q_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.index_q_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.k_norm.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.o_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.o_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.q_norm.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.0.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.0.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.0.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.1.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.1.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.1.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.10.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.10.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.10.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.100.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.100.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.100.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.101.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.101.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.101.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.102.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.102.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.102.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.103.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.103.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.103.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.104.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.104.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.104.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.105.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.105.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.105.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.106.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.106.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.106.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.107.w1.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.107.w2.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00059.safetensors", + "language_model.model.layers.52.block_sparse_moe.experts.107.w3.weight_scale": "model-00018-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.gate.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.108.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.108.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.108.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.108.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.108.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.108.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.109.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.109.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.109.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.109.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.109.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.109.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.11.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.11.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.11.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.11.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.11.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.11.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.110.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.110.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.110.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.110.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.110.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.110.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.111.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.111.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.111.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.111.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.111.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.111.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.112.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.112.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.112.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.112.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.112.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.112.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.113.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.113.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.113.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.113.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.113.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.113.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.114.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.114.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.114.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.114.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.114.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.114.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.115.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.115.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.115.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.115.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.115.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.115.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.116.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.116.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.116.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.116.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.116.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.116.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.117.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.117.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.117.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.117.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.117.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.117.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.118.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.118.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.118.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.118.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.118.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.118.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.119.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.119.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.119.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.119.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.119.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.119.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.12.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.12.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.12.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.12.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.12.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.12.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.120.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.120.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.120.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.120.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.120.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.120.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.121.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.121.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.121.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.121.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.121.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.121.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.122.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.122.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.122.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.122.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.122.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.122.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.123.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.123.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.123.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.123.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.123.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.123.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.124.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.124.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.124.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.124.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.124.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.124.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.125.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.125.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.125.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.125.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.125.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.125.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.126.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.126.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.126.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.126.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.126.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.126.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.127.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.127.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.127.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.127.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.127.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.127.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.13.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.13.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.13.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.13.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.13.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.13.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.14.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.14.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.14.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.14.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.14.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.14.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.15.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.15.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.15.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.15.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.15.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.15.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.16.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.16.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.16.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.16.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.16.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.16.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.17.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.17.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.17.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.17.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.17.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.17.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.18.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.18.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.18.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.18.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.18.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.18.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.19.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.19.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.19.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.19.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.19.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.19.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.2.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.2.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.2.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.20.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.20.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.20.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.20.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.20.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.20.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.21.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.21.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.21.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.21.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.21.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.21.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.22.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.22.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.22.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.22.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.22.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.22.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.23.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.23.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.23.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.23.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.23.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.23.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.24.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.24.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.24.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.24.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.24.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.24.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.25.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.25.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.25.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.25.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.25.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.25.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.26.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.26.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.26.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.26.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.26.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.26.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.27.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.27.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.27.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.27.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.27.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.27.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.28.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.28.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.28.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.28.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.28.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.28.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.29.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.29.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.29.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.29.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.29.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.29.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.3.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.3.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.3.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.30.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.30.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.30.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.30.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.30.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.30.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.31.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.31.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.31.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.31.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.31.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.31.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.32.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.32.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.32.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.32.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.32.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.32.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.33.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.33.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.33.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.33.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.33.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.33.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.34.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.34.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.34.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.34.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.34.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.34.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.35.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.35.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.35.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.35.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.35.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.35.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.36.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.36.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.36.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.36.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.36.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.36.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.37.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.37.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.37.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.37.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.37.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.37.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.38.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.38.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.38.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.38.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.38.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.38.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.39.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.39.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.39.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.39.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.39.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.39.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.4.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.4.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.4.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.40.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.40.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.40.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.40.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.40.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.40.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.41.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.41.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.41.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.41.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.41.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.41.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.42.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.42.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.42.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.42.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.42.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.42.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.43.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.43.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.43.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.43.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.43.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.43.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.44.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.44.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.44.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.44.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.44.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.44.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.45.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.45.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.45.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.45.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.45.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.45.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.46.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.46.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.46.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.46.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.46.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.46.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.47.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.47.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.47.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.47.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.47.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.47.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.48.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.48.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.48.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.48.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.48.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.48.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.49.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.49.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.49.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.49.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.49.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.49.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.5.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.5.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.5.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.5.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.50.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.50.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.50.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.50.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.50.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.50.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.51.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.51.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.51.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.51.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.51.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.51.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.52.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.52.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.52.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.52.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.52.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.52.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.53.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.53.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.53.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.53.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.53.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.53.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.54.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.54.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.54.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.54.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.54.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.54.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.55.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.55.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.55.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.55.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.55.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.55.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.56.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.56.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.56.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.56.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.56.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.56.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.57.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.57.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.57.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.57.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.57.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.57.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.58.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.58.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.58.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.58.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.58.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.58.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.59.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.59.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.59.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.59.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.59.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.59.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.6.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.6.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.6.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.6.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.6.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.6.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.60.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.60.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.60.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.60.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.60.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.60.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.61.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.61.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.61.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.61.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.61.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.61.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.62.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.62.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.62.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.62.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.62.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.62.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.63.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.63.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.63.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.63.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.63.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.63.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.64.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.64.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.64.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.64.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.64.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.64.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.65.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.65.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.65.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.65.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.65.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.65.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.66.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.66.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.66.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.66.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.66.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.66.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.67.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.67.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.67.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.67.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.67.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.67.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.68.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.68.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.68.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.68.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.68.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.68.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.69.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.69.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.69.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.69.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.69.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.69.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.7.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.7.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.7.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.7.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.7.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.7.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.70.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.70.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.70.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.70.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.70.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.70.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.71.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.71.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.71.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.71.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.71.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.71.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.72.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.72.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.72.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.72.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.72.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.72.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.73.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.73.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.73.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.73.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.73.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.73.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.74.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.74.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.74.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.74.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.74.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.74.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.75.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.75.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.75.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.75.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.75.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.75.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.76.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.76.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.76.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.76.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.76.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.76.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.77.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.77.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.77.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.77.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.77.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.77.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.78.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.78.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.78.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.78.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.78.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.78.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.79.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.79.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.79.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.79.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.79.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.79.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.8.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.8.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.8.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.8.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.8.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.8.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.80.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.80.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.80.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.80.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.80.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.80.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.81.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.81.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.81.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.81.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.81.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.81.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.82.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.82.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.82.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.82.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.82.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.82.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.83.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.83.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.83.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.83.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.83.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.83.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.84.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.84.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.84.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.84.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.84.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.84.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.85.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.85.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.85.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.85.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.85.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.85.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.86.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.86.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.86.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.86.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.86.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.86.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.87.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.87.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.87.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.87.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.87.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.87.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.88.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.88.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.88.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.88.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.88.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.88.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.89.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.89.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.89.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.89.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.89.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.89.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.9.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.9.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.9.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.9.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.9.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.9.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.90.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.90.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.90.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.90.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.90.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.90.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.91.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.91.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.91.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.91.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.91.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.91.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.92.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.92.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.92.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.92.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.92.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.92.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.93.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.93.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.93.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.93.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.93.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.93.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.94.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.94.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.94.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.94.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.94.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.94.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.95.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.95.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.95.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.95.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.95.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.95.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.96.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.96.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.96.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.96.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.96.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.96.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.97.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.97.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.97.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.97.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.97.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.97.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.98.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.98.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.98.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.98.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.98.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.98.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.99.w1.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.99.w1.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.99.w2.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.99.w2.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.99.w3.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.experts.99.w3.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.shared_experts.down_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.shared_experts.gate_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.shared_experts.up_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.input_layernorm.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.post_attention_layernorm.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.index_k_norm.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.index_k_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.index_k_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.index_q_norm.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.index_q_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.index_q_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.k_norm.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.k_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.k_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.o_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.o_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.q_norm.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.q_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.q_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.v_proj.weight": "model-00045-of-00059.safetensors", + "language_model.model.layers.45.self_attn.v_proj.weight_scale": "model-00045-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.gate.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.108.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.108.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.108.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.108.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.108.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.108.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.109.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.109.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.109.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.109.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.109.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.109.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.11.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.11.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.11.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.11.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.11.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.11.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.110.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.110.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.110.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.110.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.110.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.110.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.111.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.111.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.111.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.111.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.111.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.111.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.112.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.112.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.112.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.112.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.112.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.112.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.113.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.113.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.113.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.113.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.113.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.113.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.114.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.114.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.114.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.114.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.114.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.114.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.115.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.115.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.115.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.115.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.115.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.115.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.116.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.116.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.116.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.116.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.116.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.116.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.117.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.117.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.117.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.117.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.117.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.117.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.118.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.118.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.118.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.118.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.118.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.118.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.119.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.119.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.119.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.119.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.119.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.119.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.12.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.12.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.12.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.12.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.12.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.12.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.120.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.120.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.120.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.120.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.120.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.120.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.121.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.121.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.121.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.121.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.121.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.121.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.122.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.122.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.122.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.122.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.122.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.122.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.123.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.123.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.123.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.123.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.123.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.123.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.124.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.124.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.124.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.124.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.124.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.124.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.125.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.125.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.125.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.125.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.125.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.125.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.126.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.126.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.126.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.126.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.126.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.126.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.127.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.127.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.127.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.127.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.127.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.127.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.13.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.13.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.13.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.13.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.13.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.13.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.14.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.14.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.14.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.14.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.14.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.14.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.15.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.15.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.15.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.15.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.15.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.15.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.16.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.16.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.16.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.16.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.16.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.16.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.17.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.17.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.17.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.17.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.17.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.17.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.18.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.18.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.18.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.18.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.18.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.18.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.19.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.19.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.19.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.19.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.19.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.19.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.2.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.2.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.2.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.20.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.20.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.20.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.20.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.20.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.20.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.21.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.21.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.21.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.21.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.21.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.21.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.22.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.22.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.22.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.22.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.22.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.22.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.23.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.23.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.23.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.23.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.23.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.23.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.24.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.24.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.24.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.24.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.24.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.24.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.25.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.25.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.25.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.25.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.25.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.25.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.26.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.26.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.26.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.26.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.26.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.26.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.27.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.27.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.27.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.27.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.27.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.27.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.28.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.28.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.28.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.28.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.28.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.28.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.29.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.29.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.29.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.29.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.29.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.29.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.3.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.3.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.3.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.30.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.30.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.30.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.30.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.30.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.30.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.31.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.31.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.31.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.31.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.31.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.31.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.32.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.32.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.32.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.32.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.32.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.32.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.33.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.33.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.33.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.33.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.33.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.33.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.34.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.34.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.34.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.34.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.34.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.34.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.35.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.35.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.35.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.35.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.35.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.35.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.36.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.36.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.36.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.36.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.36.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.36.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.37.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.37.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.37.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.37.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.37.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.37.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.38.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.38.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.38.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.38.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.38.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.38.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.39.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.39.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.39.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.39.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.39.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.39.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.4.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.4.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.4.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.4.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.4.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.4.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.40.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.40.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.40.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.40.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.40.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.40.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.41.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.41.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.41.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.41.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.41.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.41.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.42.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.42.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.42.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.42.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.42.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.42.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.43.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.43.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.43.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.43.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.43.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.43.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.44.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.44.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.44.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.44.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.44.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.44.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.45.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.45.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.45.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.45.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.45.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.45.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.46.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.46.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.46.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.46.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.46.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.46.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.47.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.47.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.47.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.47.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.47.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.47.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.48.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.48.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.48.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.48.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.48.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.48.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.49.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.49.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.49.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.49.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.49.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.49.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.5.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.5.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.5.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.5.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.5.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.5.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.50.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.50.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.50.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.50.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.50.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.50.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.51.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.51.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.51.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.51.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.51.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.51.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.52.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.52.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.52.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.52.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.52.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.52.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.53.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.53.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.53.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.53.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.53.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.53.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.54.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.54.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.54.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.54.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.54.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.54.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.55.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.55.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.55.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.55.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.55.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.55.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.56.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.56.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.56.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.56.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.56.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.56.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.57.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.57.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.57.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.57.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.57.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.57.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.58.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.58.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.58.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.58.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.58.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.58.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.59.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.59.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.59.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.59.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.59.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.59.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.6.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.6.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.6.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.6.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.6.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.6.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.60.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.60.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.60.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.60.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.60.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.60.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.61.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.61.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.61.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.61.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.61.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.61.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.62.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.62.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.62.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.62.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.62.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.62.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.63.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.63.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.63.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.63.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.63.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.63.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.64.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.64.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.64.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.64.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.64.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.64.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.65.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.65.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.65.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.65.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.65.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.65.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.66.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.66.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.66.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.66.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.66.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.66.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.67.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.67.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.67.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.67.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.67.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.67.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.68.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.68.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.68.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.68.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.68.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.68.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.69.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.69.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.69.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.69.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.69.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.69.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.7.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.7.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.7.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.7.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.70.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.70.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.70.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.70.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.70.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.70.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.71.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.71.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.71.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.71.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.71.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.71.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.72.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.72.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.72.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.72.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.72.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.72.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.73.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.73.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.73.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.73.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.73.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.73.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.74.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.74.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.74.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.74.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.74.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.74.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.75.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.75.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.75.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.75.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.75.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.75.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.76.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.76.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.76.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.76.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.76.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.76.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.77.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.77.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.77.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.77.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.77.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.77.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.78.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.78.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.78.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.78.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.78.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.78.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.79.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.79.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.79.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.79.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.79.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.79.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.8.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.8.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.8.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.8.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.8.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.8.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.80.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.80.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.80.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.80.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.80.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.80.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.81.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.81.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.81.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.81.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.81.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.81.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.82.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.82.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.82.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.82.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.82.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.82.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.83.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.83.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.83.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.83.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.83.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.83.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.84.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.84.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.84.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.84.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.84.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.84.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.85.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.85.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.85.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.85.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.85.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.85.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.86.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.86.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.86.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.86.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.86.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.86.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.87.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.87.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.87.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.87.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.87.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.87.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.88.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.88.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.88.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.88.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.88.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.88.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.89.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.89.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.89.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.89.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.89.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.89.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.9.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.9.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.9.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.9.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.9.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.9.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.90.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.90.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.90.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.90.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.90.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.90.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.91.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.91.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.91.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.91.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.91.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.91.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.92.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.92.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.92.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.92.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.92.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.92.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.93.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.93.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.93.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.93.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.93.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.93.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.94.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.94.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.94.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.94.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.94.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.94.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.95.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.95.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.95.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.95.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.95.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.95.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.96.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.96.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.96.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.96.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.96.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.96.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.97.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.97.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.97.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.97.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.97.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.97.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.98.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.98.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.98.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.98.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.98.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.98.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.99.w1.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.99.w1.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.99.w2.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.99.w2.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.99.w3.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.experts.99.w3.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.shared_experts.down_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.shared_experts.gate_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.shared_experts.up_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.input_layernorm.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.post_attention_layernorm.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.index_k_norm.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.index_k_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.index_k_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.index_q_norm.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.index_q_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.index_q_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.k_norm.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.k_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.k_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.o_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.o_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.q_norm.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.q_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.q_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.v_proj.weight": "model-00046-of-00059.safetensors", + "language_model.model.layers.46.self_attn.v_proj.weight_scale": "model-00046-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.e_score_correction_bias": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.gate.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.0.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.0.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.0.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.1.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.1.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.1.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.10.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.10.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.10.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.10.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.10.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.10.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.100.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.100.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.100.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.100.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.100.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.100.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.101.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.101.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.101.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.101.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.101.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.101.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.102.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.102.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.102.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.102.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.102.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.102.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.103.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.103.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.103.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.103.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.103.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.103.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.104.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.104.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.104.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.104.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.104.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.104.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.105.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.105.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.105.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.105.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.105.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.105.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.106.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.106.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.106.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.106.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.106.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.106.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.107.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.107.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.107.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.107.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.107.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.107.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.108.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.108.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.108.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.108.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.108.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.108.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.109.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.109.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.109.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.109.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.109.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.109.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.11.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.11.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.11.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.11.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.11.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.11.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.110.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.110.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.110.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.110.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.110.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.110.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.111.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.111.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.111.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.111.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.111.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.111.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.112.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.112.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.112.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.112.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.112.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.112.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.113.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.113.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.113.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.113.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.113.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.113.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.114.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.114.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.114.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.114.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.114.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.114.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.115.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.115.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.115.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.115.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.115.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.115.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.116.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.116.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.116.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.116.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.116.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.116.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.117.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.117.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.117.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.117.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.117.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.117.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.118.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.118.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.118.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.118.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.118.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.118.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.119.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.119.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.119.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.119.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.119.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.119.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.12.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.12.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.12.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.12.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.12.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.12.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.120.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.120.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.120.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.120.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.120.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.120.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.121.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.121.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.121.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.121.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.121.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.121.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.122.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.122.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.122.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.122.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.122.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.122.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.123.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.123.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.123.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.123.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.123.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.123.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.124.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.124.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.124.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.124.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.124.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.124.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.125.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.125.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.125.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.125.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.125.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.125.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.126.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.126.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.126.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.126.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.126.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.126.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.127.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.127.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.127.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.127.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.127.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.127.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.13.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.13.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.13.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.13.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.13.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.13.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.14.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.14.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.14.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.14.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.14.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.14.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.15.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.15.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.15.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.15.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.15.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.15.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.16.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.16.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.16.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.16.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.16.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.16.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.17.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.17.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.17.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.17.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.17.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.17.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.18.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.18.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.18.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.18.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.18.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.18.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.19.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.19.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.19.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.19.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.19.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.19.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.2.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.2.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.2.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.20.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.20.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.20.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.20.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.20.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.20.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.21.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.21.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.21.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.21.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.21.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.21.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.22.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.22.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.22.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.22.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.22.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.22.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.23.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.23.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.23.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.23.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.23.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.23.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.24.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.24.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.24.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.24.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.24.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.24.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.25.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.25.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.25.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.25.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.25.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.25.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.26.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.26.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.26.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.26.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.26.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.26.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.27.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.27.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.27.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.27.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.27.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.27.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.28.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.28.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.28.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.28.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.28.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.28.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.29.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.29.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.29.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.29.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.29.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.29.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.3.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.3.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.3.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.30.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.30.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.30.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.30.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.30.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.30.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.31.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.31.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.31.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.31.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.31.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.31.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.32.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.32.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.32.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.32.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.32.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.32.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.33.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.33.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.33.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.33.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.33.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.33.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.34.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.34.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.34.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.34.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.34.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.34.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.35.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.35.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.35.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.35.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.35.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.35.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.36.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.36.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.36.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.36.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.36.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.36.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.37.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.37.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.37.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.37.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.37.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.37.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.38.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.38.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.38.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.38.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.38.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.38.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.39.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.39.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.39.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.39.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.39.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.39.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.4.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.4.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.4.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.40.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.40.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.40.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.40.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.40.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.40.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.41.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.41.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.41.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.41.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.41.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.41.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.42.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.42.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.42.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.42.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.42.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.42.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.43.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.43.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.43.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.43.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.43.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.43.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.44.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.44.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.44.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.44.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.44.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.44.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.45.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.45.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.45.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.45.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.45.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.45.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.46.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.46.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.46.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.46.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.46.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.46.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.47.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.47.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.47.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.47.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.47.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.47.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.48.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.48.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.48.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.48.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.48.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.48.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.49.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.49.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.49.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.49.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.49.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.49.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.5.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.5.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.5.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.50.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.50.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.50.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.50.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.50.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.50.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.51.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.51.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.51.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.51.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.51.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.51.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.52.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.52.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.52.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.52.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.52.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.52.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.53.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.53.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.53.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.53.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.53.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.53.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.54.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.54.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.54.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.54.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.54.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.54.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.55.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.55.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.55.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.55.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.55.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.55.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.56.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.56.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.56.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.56.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.56.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.56.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.57.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.57.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.57.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.57.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.57.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.57.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.58.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.58.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.58.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.58.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.58.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.58.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.59.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.59.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.59.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.59.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.59.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.59.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.6.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.6.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.6.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.60.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.60.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.60.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.60.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.60.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.60.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.61.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.61.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.61.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.61.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.61.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.61.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.62.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.62.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.62.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.62.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.62.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.62.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.63.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.63.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.63.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.63.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.63.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.63.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.64.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.64.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.64.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.64.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.64.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.64.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.65.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.65.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.65.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.65.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.65.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.65.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.66.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.66.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.66.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.66.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.66.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.66.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.67.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.67.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.67.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.67.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.67.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.67.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.68.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.68.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.68.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.68.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.68.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.68.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.69.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.69.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.69.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.69.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.69.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.69.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.7.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.7.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.7.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.70.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.70.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.70.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.70.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.70.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.70.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.71.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.71.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.71.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.71.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.71.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.71.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.72.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.72.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.72.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.72.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.72.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.72.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.73.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.73.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.73.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.73.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.73.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.73.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.74.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.74.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.74.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.74.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.74.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.74.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.75.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.75.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.75.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.75.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.75.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.75.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.76.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.76.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.76.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.76.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.76.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.76.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.77.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.77.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.77.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.77.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.77.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.77.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.78.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.78.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.78.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.78.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.78.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.78.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.79.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.79.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.79.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.79.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.79.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.79.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.8.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.8.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.8.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.8.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.8.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.8.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.80.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.80.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.80.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.80.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.80.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.80.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.81.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.81.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.81.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.81.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.81.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.81.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.82.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.82.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.82.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.82.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.82.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.82.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.83.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.83.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.83.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.83.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.83.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.83.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.84.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.84.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.84.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.84.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.84.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.84.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.85.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.85.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.85.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.85.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.85.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.85.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.86.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.86.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.86.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.86.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.86.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.86.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.87.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.87.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.87.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.87.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.87.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.87.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.88.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.88.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.88.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.88.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.88.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.88.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.89.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.89.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.89.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.89.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.89.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.89.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.9.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.9.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.9.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.9.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.9.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.9.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.90.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.90.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.90.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.90.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.90.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.90.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.91.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.91.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.91.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.91.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.91.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.91.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.92.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.92.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.92.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.92.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.92.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.92.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.93.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.93.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.93.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.93.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.93.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.93.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.94.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.94.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.94.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.94.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.94.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.94.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.95.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.95.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.95.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.95.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.95.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.95.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.96.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.96.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.96.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.96.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.96.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.96.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.97.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.97.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.97.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.97.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.97.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.97.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.98.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.98.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.98.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.98.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.98.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.98.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.99.w1.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.99.w1.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.99.w2.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.99.w2.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.99.w3.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.experts.99.w3.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.shared_experts.down_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.shared_experts.down_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.shared_experts.gate_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.shared_experts.gate_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.shared_experts.up_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.block_sparse_moe.shared_experts.up_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.index_k_norm.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.index_k_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.index_k_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.index_q_norm.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.index_q_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.index_q_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.k_norm.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.q_norm.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight_scale": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00029-of-00059.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight_scale": "model-00029-of-00059.safetensors" } } \ No newline at end of file diff --git a/quark_profile.yaml b/quark_profile.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6f2d887a44749af6aa30e45ac2e4180442256fe7 --- /dev/null +++ b/quark_profile.yaml @@ -0,0 +1,79 @@ +# Quark Profiling Results + +memory_usage: +- step: "Start" + timestamp: 1781693541.2232757 + relative_time_secs: 0.0 + cpu_memory_mb: 1543.05 + gpu_memory_mb: 286.03 + disk_read_mb: 0.0 + disk_write_mb: 0.0 +- step: "File-to-File Quantization Start" + timestamp: 1781693541.3864503 + relative_time_secs: 0.16317462921142578 + cpu_memory_mb: 1543.05 + gpu_memory_mb: 286.03 + disk_read_mb: 0.0 + disk_write_mb: 0.0 +- step: "File-to-File Quantization Start" + timestamp: 1781693541.567942 + relative_time_secs: 0.3446662425994873 + cpu_memory_mb: 1543.05 + gpu_memory_mb: 286.03 + disk_read_mb: 0.0 + disk_write_mb: 0.0 +- step: "File-to-File Quantization End" + timestamp: 1781694349.5782049 + relative_time_secs: 808.3549292087555 + cpu_memory_mb: 8711.84 + gpu_memory_mb: 284.57 + disk_read_mb: 105379.9 + disk_write_mb: 225260.07 +- step: "File-to-File Quantization End" + timestamp: 1781694349.743224 + relative_time_secs: 808.5199482440948 + cpu_memory_mb: 8711.84 + gpu_memory_mb: 284.57 + disk_read_mb: 105379.9 + disk_write_mb: 225260.07 +- step: "End" + timestamp: 1781694349.9079034 + relative_time_secs: 808.6846277713776 + cpu_memory_mb: 8711.84 + gpu_memory_mb: 284.57 + disk_read_mb: 105379.9 + disk_write_mb: 225260.07 + +# Summary Metrics +total_quantization_time_seconds: 808.6847 +peak_memory_mb: 24045.82 +peak_gpu_memory_mb: 286.03 +total_disk_read_mb: 105379.9 +total_disk_write_mb: 225260.07 + +# Metric Definitions: +# +# Checkpoint Metrics (per record): +# - step: Name of the profiling checkpoint. Common steps include: +# - "Start": Initial state when profiling begins +# - "Model Loaded": After loading the ONNX model into memory +# - "Pre-process Start/End": Before and after model preprocessing +# - "Calibration Start/End": Before and after calibration data collection +# - "Quantization (MatMulNBits) Start/End": MatMulNBits quantization phase +# - "Quantization (Static) Start/End": Static quantization phase +# - "Post-process Start/End": Before and after post-processing +# - "Fast Finetune Start/End": Before and after fast finetuning (if enabled) +# - timestamp: Unix timestamp (seconds since epoch) when this measurement was taken. Useful for correlating with external logs or events. +# - relative_time_secs: Time elapsed (in seconds) since the "Start" step. Useful for understanding the duration of each phase relative to the beginning of profiling. +# - cpu_memory_mb: Current Resident Set Size (RSS) in megabytes at this step. This includes memory from the main process and all child processes. RSS represents the portion of memory held in RAM (not swapped out). +# - gpu_memory_mb: Current GPU memory usage in megabytes. This represents actual GPU memory used by the process, including allocations from PyTorch, ONNX Runtime, TensorRT, and other frameworks. Only available when PyTorch with CUDA/ROCm is installed and GPU is available. +# - disk_read_mb: Cumulative disk bytes read (in megabytes) since the start of profiling. Measured relative to the baseline captured at the 'Start' checkpoint, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc//io, Windows; not available on macOS without root). +# - disk_write_mb: Cumulative disk bytes written (in megabytes) since the start of profiling. Measured relative to the baseline captured at the 'Start' checkpoint, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc//io, Windows; not available on macOS without root). +# +# Summary Metrics (overall): +# - total_quantization_time_seconds: Total elapsed time (in seconds) from the start of profiling to the end of the quantization process. +# - peak_memory_mb: Peak resident set size (RSS) in megabytes for the main process during the entire profiling session. On Linux, this is read from VmHWM (high water mark) in /proc//status. On Windows, this is the peak working set size. This metric may not be available on all platforms. +# - peak_gpu_memory_mb: Peak GPU memory usage in megabytes during the entire profiling session. This is the maximum GPU memory used, including allocations from PyTorch, ONNX Runtime, TensorRT, and other frameworks. Only available when PyTorch with CUDA/ROCm is installed and GPU is available. +# - total_disk_read_mb: Total disk bytes read (in megabytes) during the entire profiling session. Computed as the difference between the final and baseline cumulative read counters, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc//io, Windows; not available on macOS without root). +# - total_disk_write_mb: Total disk bytes written (in megabytes) during the entire profiling session. Computed as the difference between the final and baseline cumulative write counters, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc//io, Windows; not available on macOS without root). +# - peak_cache_dir_disk_usage_mb: Highest peak increase in disk usage (in megabytes) among all cache directories created during the profiling session, relative to each cache directory's size when monitoring started. Sampled every 1 second by recursively summing file sizes with os.scandir().